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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anlam
    -0.07
    抽查
    -0.07
     хр
    -0.07
    OfMonth
    -0.07
    助推
    -0.07
    manage
    -0.07
    범
    -0.07
    asd
    -0.06
    -network
    -0.06
    /msg
    -0.06
    POSITIVE LOGITS
    abela
    0.07
    unately
    0.07
    优雅
    0.07
     вос
    0.07
    Bow
    0.07
     внут
    0.07
     wykon
    0.07
    忏
    0.07
     кажд
    0.07
    ifacts
    0.07
    Act Density 0.011%

    No Known Activations