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

    Neuronpedia

    INDEX
    Explanations

    copper and related materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ל
    2.47
    ни
    2.38
    ри
    2.23
    ल
    2.00
    сь
    1.93
    ాన్ని
    1.92
    læ
    1.86
    larda
    1.84
    픈
    1.84
    ום
    1.84
    POSITIVE LOGITS
     iż
    1.98
     Acoust
    1.86
    ou
    1.77
     direta
    1.72
     亠
    1.71
    ap
    1.70
     vẻ
    1.69
     alas
    1.69
     Casualty
    1.67
     Achieve
    1.65
    Act Density 0.001%

    No Known Activations