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

    Neuronpedia

    INDEX
    Explanations

    ansion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     forces
    -0.07
    餐
    -0.07
    agency
    -0.07
    agram
    -0.06
     čas
    -0.06
    出し
    -0.06
     travail
    -0.06
     ﻣ
    -0.06
    conscious
    -0.06
     μου
    -0.06
    POSITIVE LOGITS
    ladığ
    0.07
    EATURE
    0.07
     Ré
    0.06
    ;}
↵
    0.06
     $('<
    0.06
    츠
    0.06
    .ToBoolean
    0.06
    ;">↵
    0.06
    ([^
    0.06
    ugin
    0.06
    Act Density 0.001%

    No Known Activations