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

    Neuronpedia

    INDEX
    Explanations

    perception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rx
    -0.07
     Rae
    -0.06
    .getP
    -0.06
     Randolph
    -0.06
     hè
    -0.06
    _pa
    -0.06
    :
↵
↵
    -0.06
    .cls
    -0.06
     px
    -0.06
    ":
↵
    -0.06
    POSITIVE LOGITS
    <Expression
    0.07
     대구
    0.07
    (MenuItem
    0.06
     undocumented
    0.06
    veys
    0.06
    ness
    0.06
     benefiting
    0.06
    NESS
    0.06
     زر
    0.06
    اصر
    0.06
    Act Density 0.162%

    No Known Activations