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

    Neuronpedia

    INDEX
    Explanations

    Wilson

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Total
    -0.07
    Attachments
    -0.07
     Pied
    -0.07
    ot
    -0.07
    _soft
    -0.07
     threatened
    -0.06
     Hampshire
    -0.06
    keterangan
    -0.06
    от
    -0.06
    _TMP
    -0.06
    POSITIVE LOGITS
    Wilson
    0.09
     Wilson
    0.08
    decision
    0.07
        ↵    ↵    ↵    ↵
    0.07
     listings
    0.07
    ALLEL
    0.07
    BASH
    0.07
    course
    0.07
    uzzi
    0.07
    PCA
    0.07
    Act Density 0.014%

    No Known Activations