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

    Neuronpedia

    INDEX
    Explanations

    positive news announcements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     It
    1.30
    In
    1.13
    It
    1.11
    1.07
    If
    1.05
     In
    1.02
     If
    1.02
    ння
    0.97
    j
    0.94
      
    0.89
    POSITIVE LOGITS
    사
    1.31
    ای
    1.11
     ク
    1.06
    に
    1.06
    ない
    1.05
    ಕ್
    0.97
    К
    0.97
    ست
    0.96
    ен
    0.94
    ου
    0.94
    Act Density 0.009%

    No Known Activations