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

    Neuronpedia

    INDEX
    Explanations

    built-in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Person
    0.80
    ியும்
    0.78
     separat
    0.75
    墘
    0.72
     capit
    0.71
     Letters
    0.71
     तास
    0.71
    Political
    0.71
     Apocalypse
    0.70
    Letters
    0.69
    POSITIVE LOGITS
    ـ
    0.89
    -
    0.75
     दर्ज
    0.73
    
    0.71
    䅧
    0.70
    з
    0.69
    )\|
    0.68
    質な
    0.68
    گر
    0.67
     لا
    0.67
    Act Density 0.082%

    No Known Activations