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

    Neuronpedia

    INDEX
    Explanations

    legal opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pow
    -0.07
    Free
    -0.07
     массив
    -0.07
    machine
    -0.06
    _MP
    -0.06
     Switzerland
    -0.06
     =====
    -0.06
    iran
    -0.06
     olabilir
    -0.06
     fro
    -0.06
    POSITIVE LOGITS
     vouchers
    0.06
    FOUND
    0.06
     deviation
    0.06
    bě
    0.06
    ்
    0.06
    Ｄ
    0.06
    (term
    0.06
    وات
    0.06
    _Function
    0.06
     �
    0.06
    Act Density 0.154%

    No Known Activations