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

    Neuronpedia

    INDEX
    Explanations

    various languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     barric
    0.41
     Vida
    0.41
     metabol
    0.39
     PRIME
    0.39
    🚦
    0.39
     Metabol
    0.38
    表記
    0.38
     agar
    0.37
    升
    0.37
     everything
    0.37
    POSITIVE LOGITS
    emphasis
    0.44
     земель
    0.41
    므
    0.40
    ক্ষম
    0.39
     сухо
    0.39
     качества
    0.39
    edm
    0.38
    opensource
    0.38
     भूप
    0.38
    ñones
    0.38
    Act Density 0.000%

    No Known Activations