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

    Neuronpedia

    INDEX
    Explanations

    parenthetical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ់
    0.55
    removal
    0.55
    Delivery
    0.54
    Concurrency
    0.52
    ubis
    0.50
    Fant
    0.50
    Thinking
    0.49
    را
    0.49
    thinking
    0.49
    ము
    0.49
    POSITIVE LOGITS
     dalam
    0.47
     Hakk
    0.47
     juin
    0.46
     considérable
    0.46
     nouveau
    0.46
     tribute
    0.46
     beat
    0.45
     nuevo
    0.45
    的孩子
    0.44
     дети
    0.44
    Act Density 0.000%

    No Known Activations