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

    Neuronpedia

    INDEX
    Explanations

    start of new sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ଫ
    1.42
    на
    1.33
    ن
    1.33
    ufig
    1.32
    வ
    1.30
     antiguas
    1.28
    ار
    1.27
    ээр
    1.24
    ्रय
    1.24
    чать
    1.23
    POSITIVE LOGITS
    t
    2.20
    adays
    2.04
    varande
    1.74
     defunct
    1.66
    here
    1.63
    ಾಗಲೇ
    1.61
    tive
    1.61
    traj
    1.60
    痞
    1.58
    tım
    1.53
    Act Density 0.110%

    No Known Activations