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
    declaration
    -0.07
    圖
    -0.07
    ruta
    -0.06
    _Post
    -0.06
    -eslint
    -0.06
     Pun
    -0.06
    Roboto
    -0.06
     pins
    -0.06
    conto
    -0.06
     prostřed
    -0.06
    POSITIVE LOGITS
     producing
    0.06
    ел
    0.06
    _wallet
    0.06
    场
    0.06
    >Main
    0.06
     *))
    0.06
    _move
    0.06
    SOR
    0.06
     Eleanor
    0.06
     callBack
    0.06
    Act Density 0.052%

    No Known Activations