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

    Neuronpedia

    INDEX
    Explanations

    bracket

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .NotNil
    -0.06
    ーネ
    -0.06
     Evropské
    -0.06
    Invariant
    -0.06
    インタ
    -0.06
     chromium
    -0.06
    <object
    -0.06
    ctrine
    -0.06
    -origin
    -0.06
     porque
    -0.06
    POSITIVE LOGITS
     LEN
    0.07
     abducted
    0.07
     мат
    0.07
     angst
    0.06
     Получ
    0.06
     '"';↵
    0.06
     случаях
    0.06
    SUR
    0.06
    /event
    0.06
    خته
    0.06
    Act Density 0.007%

    No Known Activations