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

    Neuronpedia

    INDEX
    Explanations

    ob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     witnessing
    -0.08
    [val
    -0.08
     powerhouse
    -0.08
     Char
    -0.07
     ava
    -0.07
     sorrow
    -0.07
     trav
    -0.07
    꽉
    -0.07
    雄厚
    -0.07
    (environment
    -0.07
    POSITIVE LOGITS
    _LINE
    0.07
    |int
    0.07
    Film
    0.07
    -web
    0.07
    ITCH
    0.07
    _stream
    0.07
     Quotes
    0.06
    𝘰
    0.06
    .Job
    0.06
    .direct
    0.06
    Act Density 0.001%

    No Known Activations