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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отмет
    -0.07
    الك
    -0.07
    無し�
    -0.07
     rookies
    -0.06
    REAT
    -0.06
    jmp
    -0.06
    iqué
    -0.06
    _ignore
    -0.06
    _validation
    -0.06
    女性
    -0.06
    POSITIVE LOGITS
    406
    0.06
    .cat
    0.06
    **)
    0.06
     Gap
    0.06
    $form
    0.06
     میتوان
    0.06
     samostat
    0.06
     Guantanamo
    0.06
     erg
    0.06
    BN
    0.06
    Act Density 0.066%

    No Known Activations