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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pl
    -0.07
     Penny
    -0.07
    theorem
    -0.06
    "/
    -0.06
    pees
    -0.06
    avail
    -0.06
     Increasing
    -0.06
    _ROW
    -0.06
    提高
    -0.06
     assaults
    -0.06
    POSITIVE LOGITS
    _equ
    0.07
    前に
    0.07
    ˆ
    0.06
     الخام
    0.06
     naw
    0.06
     вип
    0.06
    ymology
    0.06
     hakkında
    0.06
    ,cv
    0.06
    něm
    0.06
    Act Density 0.020%

    No Known Activations