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

    Neuronpedia

    INDEX
    Explanations

    presentation, request, reform, prevalent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Υ
    0.31
    Ě
    0.29
     Macs
    0.28
     de
    0.28
     Groot
    0.28
    MPs
    0.27
    olls
    0.26
    ૨
    0.26
    대를
    0.26
    í
    0.26
    POSITIVE LOGITS
    ...",
    0.38
    とはいえ
    0.32
    ...";
    0.31
     ..."
    0.30
    .."
    0.30
    ...',
    0.30
     {}>,
    0.29
    前者
    0.29
     ...]
    0.29
     эмне
    0.29
    Act Density 0.159%

    No Known Activations