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

    Neuronpedia

    INDEX
    Explanations

    formal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _file
    -0.07
    _BASE
    -0.07
     �
    -0.07
    -health
    -0.06
    ﾄ
    -0.06
    oooo
    -0.06
    _lines
    -0.06
     cmake
    -0.06
    _tran
    -0.06
    坪
    -0.06
    POSITIVE LOGITS
    شن
    0.07
    resolved
    0.07
     malaysia
    0.06
    789
    0.06
    [email
    0.06
     Whisper
    0.06
    estation
    0.06
    ett
    0.06
    のも
    0.06
    (phone
    0.06
    Act Density 0.055%

    No Known Activations