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

    Neuronpedia

    INDEX
    Explanations

    before, how, future, attempt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     」
    0.43
    。」
    0.41
    它
    0.41
     Drs
    0.40
    殘
    0.38
    磧
    0.38
    筮
    0.38
    There
    0.38
    $-$,
    0.37
    ↓
    0.37
    POSITIVE LOGITS
     horrendous
    0.46
     acontecimientos
    0.46
     органы
    0.45
     événements
    0.45
     сели
    0.45
     сложно
    0.45
     అత్య
    0.44
     ල
    0.44
     குழ
    0.44
     отличаются
    0.43
    Act Density 0.001%

    No Known Activations