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

    Neuronpedia

    INDEX
    Explanations

    This type of thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    üyük
    0.41
     കണ്ണ
    0.39
    に加え
    0.39
     immersive
    0.37
     ఆధ్యా
    0.37
     중요
    0.37
    Panoramic
    0.36
    த்தையும்
    0.36
     важно
    0.36
     இரண்ட
    0.36
    POSITIVE LOGITS
     type
    1.01
     kinds
    0.87
     tipo
    0.86
     types
    0.85
     kind
    0.84
     tipos
    0.80
     typu
    0.80
    タイプの
    0.78
     particular
    0.76
    type
    0.76
    Act Density 0.007%

    No Known Activations