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

    Neuronpedia

    INDEX
    Explanations

    MSDN documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'nde
    -0.07
    ��
    -0.07
     Hem
    -0.07
    /$
    -0.07
    _DECLS
    -0.06
    *****
    -0.06
    サイト
    -0.06
    Run
    -0.06
     defensive
    -0.06
    -hidden
    -0.06
    POSITIVE LOGITS
     Shaun
    0.06
    мов
    0.06
     SCN
    0.06
     โรง
    0.06
     پنج
    0.06
     врач
    0.06
     Sadece
    0.06
    _peak
    0.06
    _SEP
    0.06
     줄
    0.06
    Act Density 0.002%

    No Known Activations