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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Berg
    -0.07
     Ak
    -0.07
    compound
    -0.06
    -highlight
    -0.06
    _alert
    -0.06
     deity
    -0.06
    (elm
    -0.06
     Learn
    -0.06
    Lexer
    -0.06
     baptized
    -0.06
    POSITIVE LOGITS
    义
    0.07
     Watches
    0.07
    ounc
    0.07
    _TRY
    0.06
    м
    0.06
    _brightness
    0.06
    部門
    0.06
    과정
    0.06
     muff
    0.06
    -serving
    0.06
    Act Density 0.058%

    No Known Activations