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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Kate
    -0.08
     harm
    -0.07
     batches
    -0.07
     tělo
    -0.07
    Luke
    -0.07
    平方
    -0.06
    Dam
    -0.06
     advising
    -0.06
     pensar
    -0.06
     domicile
    -0.06
    POSITIVE LOGITS
    toBeFalsy
    0.07
    _UNICODE
    0.06
    ,...
    0.06
    /F
    0.06
    .Dir
    0.06
    εια
    0.06
    .getValue
    0.06
    ,re
    0.06
    lexical
    0.06
    $ret
    0.06
    Act Density 0.011%

    No Known Activations