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

    Neuronpedia

    INDEX
    Explanations

    Foreign short words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    065
    -0.07
    Literal
    -0.07
    Compilation
    -0.07
    ати
    -0.07
     found
    -0.07
     Disco
    -0.06
     seemed
    -0.06
     dismissal
    -0.06
    ummy
    -0.06
     supportive
    -0.06
    POSITIVE LOGITS
     кар
    0.07
     наш
    0.07
     αρ
    0.07
    нивер
    0.07
     براي
    0.06
     спок
    0.06
     integerValue
    0.06
     pir
    0.06
     дру
    0.06
     поск
    0.06
    Act Density 0.111%

    No Known Activations