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

    Neuronpedia

    INDEX
    Explanations

    Research studies/papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rituals
    -0.07
    %↵
    -0.07
    sth
    -0.07
     province
    -0.07
    Tree
    -0.07
    Detalle
    -0.06
     transporte
    -0.06
    mul
    -0.06
     ак
    -0.06
     plac
    -0.06
    POSITIVE LOGITS
     možné
    0.07
    (on
    0.06
     처음
    0.06
     Likely
    0.06
     регули
    0.06
     webView
    0.06
    thed
    0.06
     İŞ
    0.06
    boxes
    0.06
    ManagerInterface
    0.06
    Act Density 0.043%

    No Known Activations