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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to machine learning and model management

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

    Code, file paths, or commands

    np_acts-logits-general · gemini-2.0-flash

    execution, run, times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.40
    ValueStyle
    -0.39
    BeginContext
    -0.38
    bukkit
    -0.38
     informée
    -0.36
     Utf
    -0.36
    ftagPool
    -0.35
     @"/
    -0.34
    endphp
    -0.34
    phosa
    -0.33
    POSITIVE LOGITS
     odkazy
    0.54
     Schreiber
    0.53
    RegressionTest
    0.51
    protocol
    0.50
     Wikiseite
    0.49
     analysis
    0.48
    SequentialGroup
    0.48
    Protocol
    0.47
     literature
    0.47
     Huber
    0.47
    Act Density 0.436%

    No Known Activations