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

    Neuronpedia

    INDEX
    Explanations

    Domain name configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     самом
    -0.07
    396
    -0.07
     Dead
    -0.07
    iations
    -0.07
    َه
    -0.06
     apk
    -0.06
     nf
    -0.06
     strain
    -0.06
     recurse
    -0.06
     año
    -0.06
    POSITIVE LOGITS
     dishonest
    0.07
    TexParameter
    0.06
    .ValidationError
    0.06
     workaround
    0.06
    شب
    0.06
    ERVER
    0.06
    Atomic
    0.06
     Carolyn
    0.06
     oppressive
    0.06
     skate
    0.06
    Act Density 0.021%

    No Known Activations