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

    Neuronpedia

    INDEX
    Explanations

    "net

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stout
    -0.07
    忙
    -0.07
    سبب
    -0.07
    itious
    -0.06
     ",
↵
    -0.06
    AVED
    -0.06
     exped
    -0.06
    μέν
    -0.06
     Improvement
    -0.06
    _WORDS
    -0.06
    POSITIVE LOGITS
     parameter
    0.09
     Video
    0.07
     gender
    0.07
     codes
    0.07
    hesion
    0.07
     violence
    0.07
     participant
    0.07
     options
    0.06
     Parameter
    0.06
    _VIDEO
    0.06
    Act Density 0.001%

    No Known Activations