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

    Neuronpedia

    INDEX
    Explanations

    white

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atal
    -0.07
     sog
    -0.07
     dès
    -0.07
    Som
    -0.07
     ricerca
    -0.06
    idders
    -0.06
     leaks
    -0.06
    dux
    -0.06
    _account
    -0.06
    _SEQ
    -0.06
    POSITIVE LOGITS
     …
    0.07
     م
    0.07
    İTESİ
    0.06
    Whilst
    0.06
    (wp
    0.06
     comprises
    0.06
    rewrite
    0.06
    :border
    0.06
     영향
    0.06
     conforms
    0.06
    Act Density 0.001%

    No Known Activations