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

    Neuronpedia

    INDEX
    Explanations

    diet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Пос
    -0.06
    _DEFINITION
    -0.06
    _income
    -0.06
    スコ
    -0.06
    ;width
    -0.06
     misinformation
    -0.06
    .Ch
    -0.05
    दम
    -0.05
     embryos
    -0.05
     sciences
    -0.05
    POSITIVE LOGITS
     [\
    0.07
    floor
    0.07
    طب
    0.07
     Garrett
    0.07
    >\
    0.07
    ,u
    0.07
    gressive
    0.07
    렀
    0.06
    (fid
    0.06
    anner
    0.06
    Act Density 0.000%

    No Known Activations