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

    Neuronpedia

    INDEX
    Explanations

    tables and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coil
    0.61
    フオク
    0.60
    ungkan
    0.59
     Winn
    0.58
    Sung
    0.57
     linearity
    0.57
    pano
    0.56
    cone
    0.56
    wb
    0.56
    HomeController
    0.56
    POSITIVE LOGITS
     Rem
    0.83
    Rem
    0.75
     rem
    0.74
    rem
    0.71
    क्टेयर
    0.63
     noche
    0.60
    rema
    0.59
    ട്ര
    0.59
     Nacht
    0.59
    ديث
    0.59
    Act Density 0.142%

    No Known Activations