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

    Neuronpedia

    INDEX
    Explanations

    advice/tips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     util
    -0.07
    Converted
    -0.07
     Bans
    -0.07
    ™
    -0.07
    ueur
    -0.07
    Responsive
    -0.07
    .forward
    -0.07
     debilitating
    -0.06
    证券
    -0.06
     intricate
    -0.06
    POSITIVE LOGITS
    cls
    0.06
     psychologically
    0.06
     giả
    0.06
    +N
    0.06
     breaks
    0.06
     preaching
    0.06
     interviews
    0.06
     администра
    0.06
    (directory
    0.05
    ascript
    0.05
    Act Density 0.017%

    No Known Activations