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

    Neuronpedia

    INDEX
    Explanations

    most common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.66
    })
    0.63
    PRO
    0.63
     счет
    0.63
     Paese
    0.63
    PRE
    0.60
    ↵
    0.59
     peux
    0.58
     Aussi
    0.58
     mirando
    0.57
    POSITIVE LOGITS
    ्स
    0.80
     opportune
    0.78
    ojen
    0.77
    حب
    0.74
    ことを
    0.70
    ן
    0.70
    hentication
    0.70
    ੀ
    0.68
    郝
    0.68
    يات
    0.67
    Act Density 0.043%

    No Known Activations