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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives and superlatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ड़ों
    0.71
    篒
    0.71
    ください
    0.64
    abilités
    0.64
    ői
    0.63
    琍
    0.62
    cknowledg
    0.61
    FileDialog
    0.61
    ناس
    0.60
    estellten
    0.60
    POSITIVE LOGITS
     (>
    0.90
     또는
    0.82
     (+)
    0.81
    หรือ
    0.78
     atau
    0.76
     hoặc
    0.76
     (-)
    0.75
     বা
    0.74
     bzw
    0.74
     or
    0.70
    Act Density 0.005%

    No Known Activations