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

    Neuronpedia

    INDEX
    Explanations

    Real Pict, Self-Produced, Ready Stock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thisStudent
    0.58
     anthropological
    0.54
    文学
    0.54
    irteenth
    0.53
    🫤
    0.53
    পঞ্চ
    0.52
    文學
    0.52
    classAttribute
    0.52
    amending
    0.52
    立場
    0.51
    POSITIVE LOGITS
     T
    0.64
     semua
    0.64
    0.63
     B
    0.62
     harga
    0.61
     produk
    0.61
     ALL
    0.60
     C
    0.60
     Harga
    0.60
     warna
    0.59
    Act Density 0.003%

    No Known Activations