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

    Neuronpedia

    INDEX
    Explanations

    lists of numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -minded
    -0.08
     definit
    -0.07
     polo
    -0.07
     chic
    -0.06
    徹
    -0.06
    光明
    -0.06
    .getContent
    -0.06
    encies
    -0.06
    辩论
    -0.06
    逐
    -0.06
    POSITIVE LOGITS
     ratings
    0.08
    @Inject
    0.08
     KW
    0.08
     transpose
    0.08
    _VARS
    0.07
     TRACK
    0.07
     NBA
    0.07
     Industry
    0.07
     gallery
    0.07
    存在的
    0.07
    Act Density 0.015%

    No Known Activations