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

    Neuronpedia

    INDEX
    Explanations

    HTTP requests and responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Considering
    -0.08
    征
    -0.07
    (bot
    -0.07
    .Cons
    -0.07
     Accordingly
    -0.07
    槽
    -0.06
    ❌
    -0.06
     realizado
    -0.06
    China
    -0.06
     widow
    -0.06
    POSITIVE LOGITS
    美味しい
    0.08
    一台
    0.07
     ideas
    0.06
    ować
    0.06
     surrounds
    0.06
    arring
    0.06
    RESSED
    0.06
    איר
    0.06
    <<<<<<<<
    0.06
     authenticated
    0.06
    Act Density 0.002%

    No Known Activations