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

    Neuronpedia

    INDEX
    Explanations

    java

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bar
    -0.07
    🕳
    -0.07
    <footer
    -0.07
    EMAIL
    -0.07
    Ball
    -0.06
    Lemma
    -0.06
    蛤
    -0.06
    firstname
    -0.06
    启示
    -0.06
     Certificate
    -0.06
    POSITIVE LOGITS
    סכ
    0.08
     fonction
    0.08
    ST
    0.07
    inbox
    0.07
     Austria
    0.07
    ☕
    0.07
    (SQL
    0.07
    .Pool
    0.07
    争议
    0.06
     кнопк
    0.06
    Act Density 0.005%

    No Known Activations