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

    Neuronpedia

    INDEX
    Explanations

    please provide text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     potenc
    0.74
     நம்
    0.64
    如果我们
    0.63
    Occasionally
    0.61
     într
    0.61
     потенциа
    0.60
    灵活
    0.58
    Specs
    0.58
    Callable
    0.57
    potentially
    0.57
    POSITIVE LOGITS
     please
    1.08
     pls
    1.08
     necesito
    1.07
     plz
    1.05
     teks
    0.99
     text
    0.97
    粘贴
    0.96
     testo
    0.95
     plagiarism
    0.92
     texto
    0.92
    Act Density 0.518%

    No Known Activations