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

    Neuronpedia

    INDEX
    Explanations

    ir

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。她
    -0.07
    桃
    -0.07
     Shadow
    -0.06
    aka
    -0.06
     Supplements
    -0.06
     newspapers
    -0.06
     referees
    -0.06
     będą
    -0.06
    ZA
    -0.06
     Ben
    -0.06
    POSITIVE LOGITS
     scoop
    0.07
     次
    0.06
    _steps
    0.06
    849
    0.06
    exc
    0.06
     För
    0.06
    율
    0.06
    _KEYWORD
    0.06
    稿
    0.06
    CHandle
    0.06
    Act Density 0.229%

    No Known Activations