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

    Neuronpedia

    INDEX
    Explanations

    this is the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mejores
    0.40
     bolje
    0.40
     bästa
    0.39
     mieux
    0.37
    श्रेष्ठ
    0.36
    ራም
    0.36
     beste
    0.36
    琉
    0.35
     മികച്ച
    0.35
    ेत्र
    0.34
    POSITIVE LOGITS
     probably
    0.77
     THE
    0.76
     practically
    0.73
     basically
    0.71
    probably
    0.70
    THE
    0.68
     arguably
    0.65
    basically
    0.65
     pretty
    0.63
    Probably
    0.62
    Act Density 0.145%

    No Known Activations