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

    Neuronpedia

    INDEX
    Explanations

    compulsion/being forced

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #ifndef
    -0.07
     protobuf
    -0.06
    .GetDirectoryName
    -0.06
    (It
    -0.06
     prob
    -0.06
    Tes
    -0.06
    (mod
    -0.06
    ),$
    -0.06
     MySql
    -0.06
     defenseman
    -0.06
    POSITIVE LOGITS
     nightlife
    0.07
    .blue
    0.06
     mó
    0.06
    เผ
    0.06
    silver
    0.06
    _inactive
    0.06
    lassen
    0.06
     lao
    0.06
    มห
    0.06
    英
    0.06
    Act Density 0.176%

    No Known Activations