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

    Neuronpedia

    INDEX
    Explanations

    descendant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alternatively
    -0.08
    /back
    -0.07
    cipher
    -0.07
    .templates
    -0.07
    周围的
    -0.07
     tussen
    -0.07
    坏了
    -0.07
     eins
    -0.07
    ucchini
    -0.07
    _nf
    -0.07
    POSITIVE LOGITS
    ат
    0.08
     notch
    0.07
    传媒
    0.07
    试剂
    0.07
    标志着
    0.06
    гал
    0.06
    oretical
    0.06
    ious
    0.06
    het
    0.06
    模拟
    0.06
    Act Density 0.004%

    No Known Activations