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

    Neuronpedia

    INDEX
    Explanations

    recent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乗
    -0.07
    илось
    -0.07
     ребен
    -0.06
     pods
    -0.06
    -mediated
    -0.06
     kötü
    -0.06
     سلام
    -0.06
    There
    -0.06
    _mac
    -0.06
    htaking
    -0.06
    POSITIVE LOGITS
     Frm
    0.06
    森
    0.06
    стров
    0.06
    \\\
    0.06
     आत
    0.06
    constructor
    0.06
    ağ
    0.06
     Cannot
    0.06
     Ryan
    0.06
    toFloat
    0.06
    Act Density 0.008%

    No Known Activations