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

    Neuronpedia

    INDEX
    Explanations

    models

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    사지
    -0.07
     temas
    -0.06
    _ctr
    -0.06
     مراجع
    -0.06
    .Argument
    -0.06
     oficial
    -0.06
     devastation
    -0.05
    750
    -0.05
     UK
    -0.05
    Чтобы
    -0.05
    POSITIVE LOGITS
    ुट
    0.07
    VRT
    0.07
    ฐาน
    0.07
     commission
    0.07
    Hon
    0.07
     corrosion
    0.07
     soaked
    0.07
    Embed
    0.06
     dõi
    0.06
     zem
    0.06
    Act Density 0.010%

    No Known Activations