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

    Neuronpedia

    INDEX
    Explanations

    expectation, caution, respect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     artiste
    0.54
     نیا
    0.49
     axiomatic
    0.48
    जानिए
    0.48
    Нор
    0.47
    ذی
    0.47
    dfunding
    0.45
     incontro
    0.45
     שלנו
    0.45
     CRIMINAL
    0.45
    POSITIVE LOGITS
    ot
    0.52
    出
    0.49
    ost
    0.47
    oq
    0.44
    msub
    0.43
    ến
    0.42
    uq
    0.42
    িগ
    0.42
     出
    0.41
    uk
    0.41
    Act Density 0.000%

    No Known Activations