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

    Neuronpedia

    INDEX
    Explanations

    See

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wendy
    -0.07
    궨
    -0.07
     manh
    -0.07
    .strings
    -0.07
    荔枝
    -0.07
    不仅
    -0.07
    -runner
    -0.07
    gradient
    -0.07
    @Bean
    -0.07
    facet
    -0.07
    POSITIVE LOGITS
     exile
    0.07
    耋
    0.07
     hospitalized
    0.06
    awa
    0.06
     aşağıdaki
    0.06
    methodPointerType
    0.06
    妇科
    0.06
    :>
    0.06
    作家
    0.06
    对我说
    0.06
    Act Density 0.001%

    No Known Activations