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

    Neuronpedia

    INDEX
    Explanations

    numpy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gas
    -0.07
    dist
    -0.07
    Centre
    -0.07
     Insurance
    -0.06
    ngthen
    -0.06
    OX
    -0.06
     ties
    -0.06
    Visit
    -0.06
     Dickens
    -0.06
     ink
    -0.06
    POSITIVE LOGITS
     els
    0.06
     обращ
    0.06
    rgba
    0.06
     zřejmě
    0.06
    owntown
    0.06
    ові
    0.06
    lerdi
    0.06
     guessed
    0.06
     جلو
    0.06
    (exp
    0.06
    Act Density 0.027%

    No Known Activations