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

    Neuronpedia

    INDEX
    Explanations

    Measurements and quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Flags
    -0.07
    _BOTTOM
    -0.06
     bestimm
    -0.06
     Hanna
    -0.06
    asser
    -0.06
     kinda
    -0.06
     मस
    -0.06
    냥
    -0.06
     thư
    -0.06
     turkey
    -0.06
    POSITIVE LOGITS
     Hardy
    0.07
    _##
    0.07
     BOOL
    0.07
     celebrities
    0.07
     lifts
    0.07
    (div
    0.07
     bát
    0.06
    _FB
    0.06
     catching
    0.06
    DET
    0.06
    Act Density 0.157%

    No Known Activations