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

    Neuronpedia

    INDEX
    Explanations

    normal or ordinary state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     столь
    0.58
     протя
    0.58
    arris
    0.58
     विजयी
    0.58
     Hands
    0.57
     simplistic
    0.57
    colgroup
    0.56
     грав
    0.55
     colg
    0.55
    ⴳ
    0.55
    POSITIVE LOGITS
     normal
    3.21
     ordinary
    3.17
    通常の
    3.03
    普通
    3.01
    普通の
    3.00
     обы
    2.96
    normal
    2.96
    Normal
    2.92
    普通的
    2.84
     normale
    2.82
    Act Density 0.654%

    No Known Activations