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

    Neuronpedia

    INDEX
    Explanations

    say "organizations"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indie
    -0.06
    -free
    -0.06
    .putInt
    -0.06
     itching
    -0.06
     alın
    -0.06
    .Iter
    -0.06
    (bucket
    -0.06
    uario
    -0.06
    .mul
    -0.06
    modifiers
    -0.06
    POSITIVE LOGITS
    .sensor
    0.08
     Meanwhile
    0.07
    /question
    0.07
     Manual
    0.07
     consc
    0.07
     Глав
    0.06
     rebels
    0.06
     kterého
    0.06
     sofas
    0.06
     believable
    0.06
    Act Density 0.008%

    No Known Activations