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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating manner or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    த்தின்
    0.25
    verter
    0.24
    ቤት
    0.24
     മിക
    0.24
    ល
    0.24
    體的
    0.23
    music
    0.23
    avatar
    0.23
     ቤት
    0.23
    motor
    0.22
    POSITIVE LOGITS
     also
    0.29
     भी
    0.29
     Easily
    0.28
     very
    0.26
     durchaus
    0.26
    也
    0.26
     gladly
    0.26
     Possibly
    0.26
     really
    0.26
     খুব
    0.26
    Act Density 0.000%

    No Known Activations