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

    Neuronpedia

    INDEX
    Explanations

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     COVID
    -0.06
     preschool
    -0.06
    western
    -0.06
     alcohol
    -0.06
     Ocean
    -0.06
    가능
    -0.06
     fueron
    -0.06
     mensen
    -0.06
     liquid
    -0.06
    amento
    -0.06
    POSITIVE LOGITS
     baseURL
    0.07
     asympt
    0.07
    μα
    0.06
     hashtags
    0.06
    專
    0.06
     svě
    0.06
     дот
    0.06
    億
    0.06
    @RestController
    0.06
    .engine
    0.06
    Act Density 0.004%

    No Known Activations