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

    Neuronpedia

    INDEX
    Explanations

    online forum questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lev
    -0.07
    us
    -0.07
    _winner
    -0.06
     Lowell
    -0.06
     His
    -0.06
     alot
    -0.06
     remedies
    -0.06
    ούν
    -0.06
    ladığ
    -0.06
     Four
    -0.06
    POSITIVE LOGITS
    _REGISTRY
    0.07
    SG
    0.07
     розта
    0.07
     addCriterion
    0.06
    .inc
    0.06
    enberg
    0.06
    �
    0.06
    宁
    0.06
    .TRAN
    0.06
    ietf
    0.06
    Act Density 0.091%

    No Known Activations