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

    Neuronpedia

    INDEX
    Explanations

    Choose ONE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arbitrary
    0.47
     fascinated
    0.47
     વ
    0.46
    の説明
    0.46
     disagreement
    0.46
    ANS
    0.46
     and
    0.45
    UTS
    0.45
     user
    0.45
     reactivity
    0.44
    POSITIVE LOGITS
     spesies
    0.44
     반려동
    0.43
    يد
    0.43
    뚠
    0.42
    ron
    0.40
    рио
    0.40
    పి
    0.40
    热
    0.40
    隂
    0.40
    рон
    0.39
    Act Density 0.001%

    No Known Activations