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

    Neuronpedia

    INDEX
    Explanations

    code structure identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    на
    1.18
    。
    0.86
    ان
    0.84
    ド
    0.82
    一个
    0.81
    ки
    0.80
    环保
    0.79
    ك
    0.78
    我
    0.78
    Ignoring
    0.77
    POSITIVE LOGITS
     juan
    0.85
     Linen
    0.80
     mocker
    0.80
     james
    0.77
     JUAN
    0.77
     පි
    0.77
     Jus
    0.77
     kait
    0.76
    wapV
    0.76
     Dien
    0.76
    Act Density 0.001%

    No Known Activations