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

    Neuronpedia

    INDEX
    Explanations

    print statement with arguments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.11
    お
    1.03
    ام
    0.98
    Т
    0.93
    いう
    0.89
    お客
    0.88
    М
    0.87
    א
    0.87
    Ὑ
    0.87
    Σ
    0.82
    POSITIVE LOGITS
    ర్
    0.72
    р
    0.68
    ർ
    0.64
    ли
    0.64
    te
    0.62
    лити
    0.61
    нии
    0.61
    ні
    0.59
     flavonoid
    0.59
     tuve
    0.57
    Act Density 0.265%

    No Known Activations