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

    Neuronpedia

    INDEX
    Explanations

    software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :this
    -0.07
    preset
    -0.06
    Collision
    -0.06
    <|python_tag|>
    -0.06
    _review
    -0.06
    .yang
    -0.06
     eerie
    -0.06
     vyvol
    -0.06
     Sold
    -0.06
     sus
    -0.06
    POSITIVE LOGITS
     위
    0.07
     German
    0.06
    moil
    0.06
    &S
    0.06
    プリ
    0.06
     Quentin
    0.06
    ATORY
    0.06
    lectual
    0.06
    stav
    0.06
    ั
    0.06
    Act Density 0.002%

    No Known Activations