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

    Neuronpedia

    INDEX
    Explanations

    expressing opinions or beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    çoivent
    0.49
    ཿ
    0.46
    ุ
    0.45
     לא
    0.40
    PU
    0.40
    ा
    0.39
    ம்பிய
    0.37
    рити
    0.36
     doesn
    0.36
     ভাবতে
    0.36
    POSITIVE LOGITS
     Maybe
    0.51
     everyone
    0.46
     I
    0.46
     most
    0.46
     Perhaps
    0.46
     maybe
    0.46
     biggest
    0.46
    Perhaps
    0.45
     Hag
    0.44
     Everyone
    0.43
    Act Density 0.002%

    No Known Activations