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

    Neuronpedia

    INDEX
    Explanations

    languages and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    எ
    0.57
    ook
    0.53
    ired
    0.52
    oun
    0.52
     nak
    0.51
    idding
    0.51
    ουμε
    0.49
    ited
    0.49
    igated
    0.49
     q
    0.49
    POSITIVE LOGITS
     Hydraul
    0.76
     Comissão
    0.76
     ماشینونو
    0.76
     Đến
    0.76
     Clínica
    0.75
    Cantidad
    0.75
     Consejo
    0.74
     Akademii
    0.73
    También
    0.73
    Ejercicio
    0.72
    Act Density 0.034%

    No Known Activations