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

    Neuronpedia

    INDEX
    Explanations

    software licensing and disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recounts
    -0.07
     Kennedy
    -0.07
    상
    -0.07
     dimensions
    -0.06
    ponce
    -0.06
    �
    -0.06
     gratis
    -0.06
    лі
    -0.06
     *>
    -0.06
    lm
    -0.06
    POSITIVE LOGITS
    REEN
    0.06
    .openqa
    0.06
     Chill
    0.06
     sen
    0.06
     complain
    0.06
    shan
    0.06
     Leopard
    0.06
    interpre
    0.06
    trait
    0.06
    พล
    0.06
    Act Density 0.029%

    No Known Activations