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

    Neuronpedia

    INDEX
    Explanations

    asking for input or problem description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     couvertures
    0.42
    ព្រ
    0.42
    柔軟
    0.42
    rought
    0.40
    獷
    0.40
     agak
    0.40
    healing
    0.40
    catering
    0.40
    countable
    0.39
    ರಳ
    0.39
    POSITIVE LOGITS
     question
    0.61
    完整的
    0.55
     Question
    0.54
     reproducible
    0.54
     প্রশ্ন
    0.54
     problem
    0.53
    Question
    0.53
     context
    0.52
     contexte
    0.52
    Inputs
    0.52
    Act Density 0.016%

    No Known Activations