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

    Neuronpedia

    INDEX
    Explanations

    the/your followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulumi
    -0.09
    .tbl
    -0.08
    \n\n
    -0.08
     MacDonald
    -0.08
    âĺĨ
    -0.07
     nuest
    -0.07
     ...\n\n\n\n
    -0.07
    stoupil
    -0.07
    Äļ
    -0.07
    çĽijåIJ¬é¡µéĿ¢
    -0.07
    POSITIVE LOGITS
    isko
    0.08
    orses
    0.08
     selves
    0.07
    .CustomButton
    0.07
     aforementioned
    0.07
    amilia
    0.07
    Unchecked
    0.07
     nouvel
    0.07
    _Invoke
    0.07
    uxtap
    0.07
    Act Density 0.213%

    No Known Activations