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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >`;↵
    -0.09
     mediterr
    -0.08
    _SIGNATURE
    -0.08
     صفحه
    -0.08
    .bmp
    -0.08
     Caesar
    -0.08
    _ca
    -0.07
     منع
    -0.07
     accusations
    -0.07
    (HWND
    -0.07
    POSITIVE LOGITS
     probabilities
    0.15
     average
    0.14
    .average
    0.14
    average
    0.14
    Average
    0.13
     averaged
    0.13
     Average
    0.13
     unconditional
    0.13
     probabil
    0.13
     probability
    0.12
    Act Density 0.026%

    No Known Activations