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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     KY
    -0.07
    pr
    -0.07
    Kelly
    -0.07
    KY
    -0.07
    former
    -0.07
    Email
    -0.06
    Roger
    -0.06
    Jonathan
    -0.06
    нуть
    -0.06
     листь
    -0.06
    POSITIVE LOGITS
     unsuccessfully
    0.07
    менш
    0.06
    _STYLE
    0.06
    ादन
    0.06
    =pos
    0.06
    ульт
    0.06
     bás
    0.06
     Eag
    0.06
     jpeg
    0.06
    =head
    0.06
    Act Density 0.077%

    No Known Activations