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

    Neuronpedia

    INDEX
    Explanations

    Old MajorIt sitsEvent 1Soft lighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pela
    0.65
     nörd
    0.61
     ]];
    0.59
     forhold
    0.57
     considérer
    0.57
    ']")
    0.57
     vorhand
    0.57
     junto
    0.56
     podía
    0.56
     dois
    0.55
    POSITIVE LOGITS
    স
    0.58
    ts
    0.56
    자
    0.55
     Kini
    0.55
    tu
    0.54
    제
    0.54
    บ
    0.53
    ม
    0.52
    ని
    0.52
    ta
    0.52
    Act Density 0.000%

    No Known Activations