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

    Neuronpedia

    INDEX
    Explanations

    sides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YPD
    -0.07
    .Replace
    -0.07
    Storyboard
    -0.06
     Kee
    -0.06
     nextProps
    -0.06
     debating
    -0.06
    αι
    -0.06
     شناخته
    -0.06
    �
    -0.06
     ngừng
    -0.06
    POSITIVE LOGITS
    (rx
    0.07
    annotation
    0.07
    _stage
    0.07
    mination
    0.06
    iten
    0.06
     genitals
    0.06
     W
    0.06
    Enabled
    0.06
     sentences
    0.06
    uffix
    0.06
    Act Density 0.004%

    No Known Activations