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

    Neuronpedia

    INDEX
    Explanations

    why not violet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    培養
    0.48
     건강
    0.46
     ಚುನ
    0.46
    စ္
    0.43
    健康
    0.42
    ंच्या
    0.42
    Ⲏ
    0.42
    acariy
    0.41
    growing
    0.41
    機関
    0.41
    POSITIVE LOGITS
     requirement
    0.50
     Advantage
    0.49
     value
    0.48
     hunk
    0.48
     rims
    0.46
     advantage
    0.46
     tubo
    0.45
     nickel
    0.45
    lamps
    0.45
     wartość
    0.45
    Act Density 0.006%

    No Known Activations