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

    Neuronpedia

    INDEX
    Explanations

    peace, crises, or wrongdoing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    金额
    0.47
    țile
    0.46
    高达
    0.45
    جميع
    0.44
    规格
    0.43
    器
    0.42
    Equipment
    0.42
    。）
    0.42
    শিপ
    0.42
    Xx
    0.41
    POSITIVE LOGITS
    t
    0.77
     wrongdoing
    0.46
     crime
    0.45
     campaigning
    0.45
     crises
    0.44
    <0x80>
    0.44
     violent
    0.43
     corps
    0.42
     परंतु
    0.41
     असून
    0.41
    Act Density 0.003%

    No Known Activations