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

    Neuronpedia

    INDEX
    Explanations

    no undo, no recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    we
    0.50
    into
    0.49
    e
    0.44
     Angel
    0.44
     into
    0.44
    纯
    0.44
    in
    0.43
    IN
    0.43
    about
    0.43
     brittle
    0.43
    POSITIVE LOGITS
    thione
    0.49
    мір
    0.47
    ریٹر
    0.47
    рит
    0.47
     نتی
    0.46
    وری
    0.45
    ໃຫ
    0.45
     гру
    0.45
     или
    0.44
     тази
    0.44
    Act Density 0.003%

    No Known Activations