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

    Neuronpedia

    INDEX
    Explanations

    laws

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blanc
    -0.07
    .BigInteger
    -0.07
     IntPtr
    -0.07
     rewritten
    -0.07
    IntPtr
    -0.07
    quals
    -0.07
    欢迎您
    -0.07
    ––
    -0.07
     mies
    -0.07
    𪨰
    -0.07
    POSITIVE LOGITS
    -media
    0.08
    הגנה
    0.07
    гр
    0.07
     acknowled
    0.07
     אף
    0.07
    épo
    0.06
    .FormBorderStyle
    0.06
    ")){↵
    0.06
    _scr
    0.06
    `.↵
    0.06
    Act Density 0.006%

    No Known Activations