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

    Neuronpedia

    INDEX
    Explanations

    Filipino languages and origins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     luminal
    0.42
    lum
    0.41
    ieson
    0.40
    דו
    0.39
     contracting
    0.38
     Lum
    0.37
     هش
    0.37
    結
    0.37
    破碎
    0.37
    者的
    0.36
    POSITIVE LOGITS
     Norte
    0.46
    ândia
    0.44
     Sur
    0.44
    andia
    0.44
    SUR
    0.43
    Sur
    0.42
     Fant
    0.42
    ocos
    0.42
     SUR
    0.41
     CANT
    0.40
    Act Density 0.000%

    No Known Activations