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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有所帮助
    -0.08
     DEVELO
    -0.07
     avenues
    -0.07
     Toys
    -0.07
     Tow
    -0.07
     ISBN
    -0.07
    稳妥
    -0.07
    בדק
    -0.07
    不小的
    -0.06
    泰山
    -0.06
    POSITIVE LOGITS
     the
    0.08
    wick
    0.08
    mapped
    0.07
     minValue
    0.07
     mulher
    0.07
    _WORDS
    0.07
    他们是
    0.07
    <translation
    0.07
     yi
    0.07
    изма
    0.07
    Act Density 0.158%

    No Known Activations