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

    Neuronpedia

    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getValue
    -0.07
    .getWidth
    -0.07
    .ge
    -0.06
    /Internal
    -0.06
     المغ
    -0.06
     тип
    -0.06
    ToInt
    -0.06
     Пер
    -0.06
     верх
    -0.06
    Verifier
    -0.06
    POSITIVE LOGITS
    FW
    0.07
    lj
    0.06
     flea
    0.06
    ashion
    0.06
     pož
    0.06
    SnackBar
    0.06
    ne
    0.06
     Madison
    0.06
    izzard
    0.06
    oldem
    0.06
    Act Density 0.008%

    No Known Activations