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

    Neuronpedia

    INDEX
    Explanations

    article/paper extracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urgery
    -0.07
    stype
    -0.07
     Fischer
    -0.07
    (sh
    -0.06
    (Note
    -0.06
     onError
    -0.06
    Type
    -0.06
    agnosis
    -0.06
    Sale
    -0.06
    hei
    -0.06
    POSITIVE LOGITS
    สาว
    0.06
    �
    0.06
     україн
    0.06
    専
    0.06
     banged
    0.06
     references
    0.06
    を持
    0.06
    .seek
    0.06
     staff
    0.06
     inception
    0.06
    Act Density 0.123%

    No Known Activations