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

    Neuronpedia

    INDEX
    Explanations

    social

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    923
    -0.07
    teil
    -0.07
     gan
    -0.06
    ’den
    -0.06
     negocio
    -0.06
    /interfaces
    -0.06
    RDD
    -0.06
     komunik
    -0.06
     hry
    -0.06
    ("%
    -0.06
    POSITIVE LOGITS
    atta
    0.07
     Ack
    0.07
     شیمی
    0.07
     Você
    0.07
    τω
    0.07
    .Many
    0.07
    __':↵
    0.06
    صال
    0.06
     Chess
    0.06
     Strategic
    0.06
    Act Density 0.264%

    No Known Activations