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

    Neuronpedia

    INDEX
    Explanations

    ary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blinds
    -0.07
     excellent
    -0.06
    .esp
    -0.06
     carrot
    -0.06
     valide
    -0.06
     Nas
    -0.06
    <Link
    -0.06
     тран
    -0.06
    jectives
    -0.06
     attraction
    -0.06
    POSITIVE LOGITS
     dietary
    0.14
     Dietary
    0.13
    May
    0.07
    )object
    0.07
     Timothy
    0.07
     NSRange
    0.07
    $query
    0.07
    \Blueprint
    0.06
     Darth
    0.06
    SectionsIn
    0.06
    Act Density 0.002%

    No Known Activations