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

    Neuronpedia

    INDEX
    Explanations

    code, math, formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Candy
    -0.07
     violate
    -0.07
     Пет
    -0.07
    찌
    -0.07
     دن
    -0.06
    .grey
    -0.06
     SVN
    -0.06
     Than
    -0.06
     省
    -0.06
    武
    -0.06
    POSITIVE LOGITS
     наблю
    0.07
    ?",
    0.06
     "><
    0.06
    …
    0.06
    Rib
    0.06
    _FIND
    0.06
    .','
    0.06
    ód
    0.06
    recio
    0.06
    }/#{
    0.06
    Act Density 0.000%

    No Known Activations