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

    Neuronpedia

    INDEX
    Explanations

    specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     阅读全文
    0.27
     eSIM
    0.26
    ERSHIP
    0.26
    ്യത
    0.26
    쿱
    0.26
    㿝
    0.26
    ясплат
    0.26
    แนน
    0.26
     انتخابات
    0.26
    🅰
    0.26
    POSITIVE LOGITS
    il
    0.31
    h
    0.31
    ol
    0.30
    ia
    0.30
    ul
    0.29
    ir
    0.28
    is
    0.28
    ac
    0.27
    as
    0.27
    io
    0.27
    Act Density 0.062%

    No Known Activations