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

    Neuronpedia

    INDEX
    Explanations

    salsas, dañando, Jalapeños,Senha

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Toward
    0.41
     Toe
    0.41
     `:`
    0.40
     зак
    0.40
     অস্ত
    0.39
     Midwest
    0.39
    Toe
    0.38
    ழுக
    0.38
    zyst
    0.38
     २०२
    0.38
    POSITIVE LOGITS
    ñ
    1.20
     ñ
    1.07
    Ñ
    1.02
    ña
    1.02
    ño
    1.00
    ñas
    1.00
    ños
    0.95
     Ñ
    0.94
    ÑA
    0.86
    ñar
    0.86
    Act Density 0.011%

    No Known Activations