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

    Neuronpedia

    INDEX
    Explanations

    surveys and survey platforms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Leap
    0.52
     Cognitive
    0.44
    EventRecorder
    0.43
     Scenario
    0.42
     TAS
    0.42
    考試
    0.42
     Exams
    0.42
    తి
    0.41
    ทด
    0.41
    栘
    0.41
    POSITIVE LOGITS
    炸
    0.47
     cooperación
    0.44
    feo
    0.44
     doen
    0.43
    onnaise
    0.43
    Peso
    0.42
    5
    0.42
     neglects
    0.41
    に応
    0.41
     yaptı
    0.41
    Act Density 0.002%

    No Known Activations