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

    Neuronpedia

    INDEX
    Explanations

    B

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Stra
    -0.07
    udence
    -0.07
    isposable
    -0.06
    Spoiler
    -0.06
    .method
    -0.06
    DefaultCellStyle
    -0.06
    Pre
    -0.06
    Як
    -0.06
    แกรม
    -0.06
     forControlEvents
    -0.06
    POSITIVE LOGITS
    िवस
    0.06
    _bet
    0.06
     ($(
    0.06
    (dist
    0.06
    /sample
    0.06
     sheds
    0.06
     Malaysian
    0.06
    _hash
    0.06
    /m
    0.06
     mekan
    0.06
    Act Density 0.001%

    No Known Activations