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

    Neuronpedia

    INDEX
    Explanations

    xml version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mselves
    2.43
    اً
    2.07
    lasso
    1.97
    matic
    1.95
    était
    1.94
    ことができます
    1.92
    dove
    1.91
    don
    1.91
    ẫ
    1.87
    ensä
    1.86
    POSITIVE LOGITS
    на
    3.41
    ق
    2.94
    ch
    2.76
     sheer
    2.49
    }^{+}$
    2.22
     kracht
    2.15
    at
    2.14
    наў
    2.07
    बारक
    2.03
    𝓊
    2.02
    Act Density 0.001%

    No Known Activations