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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OrderBy
    -0.07
    annotate
    -0.07
     Landscape
    -0.07
    تبه
    -0.07
    .opensource
    -0.07
    عار
    -0.07
    ænd
    -0.07
    된
    -0.06
    ableView
    -0.06
    unbind
    -0.06
    POSITIVE LOGITS
     flavours
    0.06
     pouch
    0.06
    (ms
    0.06
     mp
    0.06
     caches
    0.06
    �行
    0.06
    ":""
    0.06
     TE
    0.06
    anie
    0.06
     dissip
    0.06
    Act Density 0.108%

    No Known Activations