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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     widgets
    -0.07
     Certain
    -0.07
     مختلف
    -0.07
     shortcuts
    -0.07
     depth
    -0.07
     FIND
    -0.07
    跋
    -0.07
     Eternal
    -0.07
     Judith
    -0.06
    olute
    -0.06
    POSITIVE LOGITS
     ahora
    0.09
     ref
    0.07
    _ends
    0.07
    𬘡
    0.07
    jah
    0.07
    clarsimp
    0.07
     pobli
    0.07
    𬶟
    0.06
    לחם
    0.06
    Ст
    0.06
    Act Density 0.006%

    No Known Activations