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

    Neuronpedia

    INDEX
    Explanations

    active

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revamped
    -0.07
     bean
    -0.07
    pluck
    -0.07
     бет
    -0.07
     verifier
    -0.06
     Streams
    -0.06
     Bean
    -0.06
    �
    -0.06
    texto
    -0.06
    共
    -0.06
    POSITIVE LOGITS
     direkt
    0.07
     disciples
    0.07
     nominations
    0.07
    _UNIFORM
    0.06
     coincidence
    0.06
     �
    0.06
    ;",↵
    0.06
     gar
    0.06
    ód
    0.06
     intimately
    0.06
    Act Density 0.002%

    No Known Activations