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

    Neuronpedia

    INDEX
    Explanations

    android activity declaration or usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ayutt
    0.68
    hadow
    0.61
    й
    0.61
     apariencia
    0.60
     yaşayan
    0.60
    ॉम
    0.59
    ifer
    0.59
    Cemento
    0.59
    珽
    0.58
     Potatoes
    0.58
    POSITIVE LOGITS
    w
    0.74
    t
    0.73
    ll
    0.66
    y
    0.64
    d
    0.63
    ó
    0.63
    k
    0.63
    é
    0.63
    g
    0.62
    не
    0.62
    Act Density 0.002%

    No Known Activations