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

    Neuronpedia

    INDEX
    Explanations

    percentage calculation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    诗人
    0.49
    ('['
    0.42
     kinemat
    0.42
    迁
    0.41
     kinematics
    0.40
    寂
    0.40
     krzy
    0.39
    }',
    0.39
     фаразлары
    0.39
     transport
    0.38
    POSITIVE LOGITS
     percentage
    0.84
     percentuale
    0.84
     Percentage
    0.77
     percentages
    0.77
    percentage
    0.76
    百分
    0.75
     процен
    0.74
     процент
    0.74
    Percentage
    0.73
     porcentaje
    0.72
    Act Density 0.244%

    No Known Activations