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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buen
    -0.08
    一�
    -0.08
     GtkWidget
    -0.07
    _ALLOWED
    -0.07
    uchos
    -0.07
     newsp
    -0.07
     dealloc
    -0.07
     mrb
    -0.07
    🥭
    -0.07
     Pok
    -0.07
    POSITIVE LOGITS
     Rever
    0.06
    *'
    0.06
    はじめ
    0.06
    '));
↵
    0.06
    ורות
    0.06
     crisis
    0.06
     וכ
    0.06
    xl
    0.06
    一下子
    0.06
    toString
    0.06
    Act Density 0.106%

    No Known Activations