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

    Neuronpedia

    INDEX
    Explanations

    specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    茷
    0.43
     Saratoga
    0.43
     ARI
    0.42
    霝
    0.42
    ویی
    0.42
    اٹ
    0.41
    筮
    0.40
    אנ
    0.40
    䨘
    0.40
     carr
    0.40
    POSITIVE LOGITS
     tomando
    0.55
    taking
    0.52
    idencia
    0.52
    после
    0.50
    ickým
    0.48
    initializing
    0.48
     हेल्दी
    0.48
    "<
    0.47
    üssel
    0.46
    elim
    0.45
    Act Density 0.006%

    No Known Activations