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

    Neuronpedia

    INDEX
    Explanations

    books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Thumbnail
    -0.07
     catch
    -0.06
     drink
    -0.06
     elbows
    -0.06
    _ca
    -0.06
     cupid
    -0.06
     Load
    -0.06
    _count
    -0.06
    Going
    -0.06
     quarantine
    -0.06
    POSITIVE LOGITS
    ernetes
    0.07
    ิว
    0.06
    .intellij
    0.06
    uD
    0.06
    دة
    0.06
    aviest
    0.06
     grande
    0.06
    Lights
    0.06
     y
    0.06
    -ext
    0.06
    Act Density 0.033%

    No Known Activations