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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bedrooms
    -0.06
    ,False
    -0.06
     boob
    -0.06
    _good
    -0.06
     elements
    -0.06
     Pence
    -0.06
    ?}",
    -0.06
    Roz
    -0.06
    issues
    -0.06
     поля
    -0.06
    POSITIVE LOGITS
    似的
    0.07
    955
    0.07
    getLast
    0.07
    性的
    0.06
    ��
    0.06
    Iter
    0.06
    __()↵↵
    0.06
    ►
    0.06
     Dış
    0.06
     español
    0.06
    Act Density 0.073%

    No Known Activations