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

    Neuronpedia

    INDEX
    Explanations

    )

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    さまざまな
    0.71
     வகைகள்
    0.70
    หลากหลาย
    0.68
     semuanya
    0.63
     다양한
    0.63
     ambitions
    0.61
    фы
    0.61
     felices
    0.61
     monopolies
    0.61
     comedies
    0.61
    POSITIVE LOGITS
     S
    0.72
     P
    0.71
     C
    0.67
     F
    0.66
     L
    0.65
     กับ
    0.65
     Dept
    0.64
     H
    0.63
     Airport
    0.62
     Ка
    0.61
    Act Density 0.000%

    No Known Activations