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

    Neuronpedia

    INDEX
    Explanations

    certain medical conditions and their implications

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

    failure

    np_acts-logits-general · gemini-2.0-flash

    unsuccessful outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.65
    joyed
    -0.59
     HomeController
    -0.57
    исленность
    -0.56
    PositiveButton
    -0.54
    HasBeenSet
    -0.54
     ISNI
    -0.53
     delighted
    -0.52
     Roskov
    -0.51
    strut
    -0.50
    POSITIVE LOGITS
     failed
    1.14
     failure
    1.09
     실패
    1.01
     Failed
    0.96
     fail
    0.96
     FAILED
    0.94
    failure
    0.93
    fail
    0.93
     failures
    0.93
     unsuccessful
    0.92
    Act Density 0.200%

    No Known Activations