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

    Neuronpedia

    INDEX
    Explanations

    mos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (','
    -0.08
    它的
    -0.07
    como
    -0.07
    ["
    -0.07
    Successfully
    -0.07
     )(
    -0.07
    ʈ
    -0.07
    -chat
    -0.06
    _le
    -0.06
    ,*
    -0.06
    POSITIVE LOGITS
    _MINOR
    0.07
    guna
    0.07
     dancer
    0.07
    ()):↵
    0.07
     entsprech
    0.07
     necessities
    0.07
    _five
    0.07
    /Open
    0.07
    חיל
    0.07
     XSS
    0.07
    Act Density 0.461%

    No Known Activations