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

    Neuronpedia

    INDEX
    Explanations

    tasked, depends, identify, how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     કંપની
    0.48
     крупные
    0.46
    ステル
    0.41
     grupos
    0.41
     табле
    0.41
     брен
    0.41
    Ր
    0.40
     группа
    0.40
     компания
    0.40
     கமல்
    0.39
    POSITIVE LOGITS
    は
    0.45
    은
    0.41
    Final
    0.40
     könnte
    0.40
     endlich
    0.39
    を開始
    0.39
     amending
    0.39
     impro
    0.38
    orov
    0.38
    aktual
    0.38
    Act Density 0.003%

    No Known Activations