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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    łożyć
    -0.08
     Hungarian
    -0.07
     basement
    -0.07
    pesan
    -0.07
     potrze
    -0.07
    .MiddleLeft
    -0.07
    跸
    -0.06
    Phi
    -0.06
     Phonetic
    -0.06
    ⎣
    -0.06
    POSITIVE LOGITS
    行动计划
    0.08
    iid
    0.08
    __('
    0.08
    _rules
    0.07
    itech
    0.07
    عرف
    0.07
    อก
    0.07
    ировка
    0.07
    _estimator
    0.07
    protocol
    0.07
    Act Density 0.003%

    No Known Activations