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

    Neuronpedia

    INDEX
    Explanations

    how

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jich
    -0.06
    lon
    -0.06
    Ut
    -0.06
    ,F
    -0.06
    ucas
    -0.06
    Nach
    -0.06
    _Id
    -0.06
    ‌ن
    -0.06
     casualties
    -0.06
    rophic
    -0.06
    POSITIVE LOGITS
     how
    0.08
     науч
    0.07
    ImageUrl
    0.07
    播放
    0.06
     международ
    0.06
    .visible
    0.06
     scholars
    0.06
     elbow
    0.06
    �
    0.06
    され
    0.06
    Act Density 0.035%

    No Known Activations