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

    Neuronpedia

    INDEX
    Explanations

    susp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (fout
    -0.07
    ARIO
    -0.07
    外国语
    -0.07
    =len
    -0.07
    .nlm
    -0.07
    $$
    -0.07
     Psych
    -0.07
    쩃
    -0.06
    _LINES
    -0.06
     למע
    -0.06
    POSITIVE LOGITS
     itching
    0.07
    תקן
    0.07
    参加了
    0.07
     trọng
    0.07
    ثقة
    0.07
     pivotal
    0.06
    これを
    0.06
     какие
    0.06
    ��
    0.06
    declaring
    0.06
    Act Density 0.006%

    No Known Activations