Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    data and metrics that highlight limitations, arguments, and inconsistencies in various studies and analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Criticizing a previous statement

    np_acts-logits-general · gemini-2.0-flash

    inadequate analysis or statement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    انيف
    -0.60
     AssemblyTitle
    -0.57
    BagConstraints
    -0.56
     occupé
    -0.55
    initializeApp
    -0.54
    Бахар
    -0.53
     Happen
    -0.52
    fml
    -0.52
    feof
    -0.52
     MediaType
    -0.51
    POSITIVE LOGITS
     fails
    1.16
     insufficient
    1.15
     inadequate
    1.11
     misses
    1.02
     fail
    0.96
     inadequ
    0.95
     insufic
    0.91
     failed
    0.90
     ineffective
    0.89
     ignores
    0.89
    Act Density 0.839%

    No Known Activations