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

    Neuronpedia

    INDEX
    Explanations

    management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     piloto
    -0.09
     паспорт
    -0.08
    徴
    -0.08
    仕様
    -0.08
     roadmap
    -0.08
    တော့
    -0.07
     نقدم
    -0.07
     pilotos
    -0.07
    .matches
    -0.07
    套路
    -0.07
    POSITIVE LOGITS
     condem
    0.08
     insect
    0.07
    (transform
    0.07
     lean
    0.07
     bearish
    0.07
     Kamu
    0.07
     Buen
    0.07
     mistakenly
    0.07
     subscribing
    0.07
    ably
    0.07
    Act Density 0.013%

    No Known Activations