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

    Neuronpedia

    INDEX
    Explanations

    .String

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    834
    -0.07
    iazza
    -0.07
     W
    -0.07
     nob
    -0.06
    565
    -0.06
    W
    -0.06
    Sanders
    -0.06
     lam
    -0.06
    pull
    -0.06
    deer
    -0.06
    POSITIVE LOGITS
    .String
    0.16
    .Integer
    0.10
    /String
    0.07
    зя
    0.07
     práv
    0.07
     GEN
    0.07
    /')
    0.06
     thời
    0.06
    redirectToRoute
    0.06
     insure
    0.06
    Act Density 0.002%

    No Known Activations