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

    Neuronpedia

    INDEX
    Explanations

    testing/toxicology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    people
    -0.07
    owel
    -0.06
    联网
    -0.06
    substring
    -0.06
     GOODMAN
    -0.06
    depth
    -0.06
     embroidered
    -0.06
    .move
    -0.06
    .Shapes
    -0.06
    just
    -0.06
    POSITIVE LOGITS
    発
    0.07
     mnoho
    0.06
    $('.
    0.06
     Honda
    0.06
    Honda
    0.06
     مسئول
    0.06
     рекоменда
    0.06
    antwort
    0.06
    \Table
    0.06
     crist
    0.06
    Act Density 0.045%

    No Known Activations