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

    Neuronpedia

    INDEX
    Explanations

    née

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .before
    -0.06
    _LANG
    -0.06
     lawyers
    -0.06
     differs
    -0.06
    ost
    -0.06
     Flask
    -0.06
     rows
    -0.06
    frared
    -0.06
    _cross
    -0.06
    eyes
    -0.06
    POSITIVE LOGITS
     fv
    0.07
    Profile
    0.07
     своє
    0.07
     mimeType
    0.07
     mệnh
    0.07
    （平成
    0.06
     autobi
    0.06
    Michelle
    0.06
    cope
    0.06
    754
    0.06
    Act Density 0.003%

    No Known Activations