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

    Neuronpedia

    INDEX
    Explanations

    general text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Values
    -0.07
    _lex
    -0.07
    ká
    -0.07
     ba
    -0.07
     qb
    -0.06
     LOT
    -0.06
     oldest
    -0.06
    .Hidden
    -0.06
    	first
    -0.06
     анализ
    -0.06
    POSITIVE LOGITS
    ！↵↵↵↵
    0.07
     $
    0.06
     Slim
    0.06
    により
    0.06
     andre
    0.06
     snag
    0.06
    ------↵
    0.06
    _APP
    0.06
    акс
    0.06
    vt
    0.05
    Act Density 0.000%

    No Known Activations