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

    Neuronpedia

    INDEX
    Explanations

    structured data markup (Schema)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ات
    0.90
    นั้น
    0.89
    Cabe
    0.86
    و
    0.86
    نا
    0.85
    satz
    0.84
    essero
    0.84
    antan
    0.83
    جموعة
    0.83
    اؤ
    0.82
    POSITIVE LOGITS
     owns
    1.00
     vivo
    0.88
     respects
    0.87
     whereabouts
    0.86
     Sikh
    0.85
     menjalani
    0.85
    ્રોલ
    0.85
    ian
    0.84
    ')}
    0.84
     Bollywood
    0.83
    Act Density 0.003%

    No Known Activations