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

    Neuronpedia

    INDEX
    Explanations

    0 to numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    on
    0.53
    oph
    0.48
    (
    0.47
    s
    0.46
    '
    0.45
     brothers
    0.44
    frac
    0.44
     amine
    0.44
    1
    0.44
     comparator
    0.44
    POSITIVE LOGITS
     letteratura
    0.57
    碰撞
    0.54
     முடிக்க
    0.50
    सना
    0.48
    みる
    0.46
     অল্প
    0.46
     பல்வேறு
    0.45
     Verlust
    0.44
     வர
    0.44
     Weapons
    0.44
    Act Density 0.000%

    No Known Activations