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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ندار
    -0.07
     melt
    -0.06
     comprises
    -0.06
    фи
    -0.06
    utter
    -0.06
    只是
    -0.06
    _c
    -0.06
     composition
    -0.06
    Details
    -0.06
     зелен
    -0.06
    POSITIVE LOGITS
     inplace
    0.07
    using
    0.07
    ags
    0.07
     Wells
    0.07
    uch
    0.07
    -rate
    0.06
    among
    0.06
    emp
    0.06
    /
↵
↵
    0.06
    _group
    0.06
    Act Density 0.037%

    No Known Activations