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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    照料
    -0.07
    divide
    -0.07
    מדריך
    -0.07
    Lady
    -0.07
    表达了
    -0.07
    抱着
    -0.06
    (INPUT
    -0.06
     Под
    -0.06
     Вы
    -0.06
     transmitted
    -0.06
    POSITIVE LOGITS
    슘
    0.08
     unc
    0.07
     Piano
    0.07
     القرار
    0.07
    馒
    0.07
     maternity
    0.07
     plates
    0.07
    怅
    0.07
    _p
    0.07
    contract
    0.07
    Act Density 0.000%

    No Known Activations