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

    Neuronpedia

    INDEX
    Explanations

    Redacting information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ivory
    -0.07
    ﺆ
    -0.07
    _manager
    -0.07
    泮
    -0.06
     Coffee
    -0.06
    _LE
    -0.06
    .undo
    -0.06
     TOOL
    -0.06
    蜉
    -0.06
    _ENCOD
    -0.06
    POSITIVE LOGITS
    }}">↵
    0.07
     لما
    0.07
    estimate
    0.07
    )`
    0.07
    𝘴
    0.07
     numeric
    0.07
     artículo
    0.07
    ▷
    0.07
     Earlier
    0.07
     actualizar
    0.07
    Act Density 0.013%

    No Known Activations