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

    Neuronpedia

    INDEX
    Explanations

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scorching
    0.59
     swoop
    0.59
     deceased
    0.58
     roasted
    0.58
    ,
    0.57
     corresponding
    0.56
     orange
    0.55
     zero
    0.55
     unspecified
    0.55
    roasted
    0.55
    POSITIVE LOGITS
    ່ງ
    0.84
    समाचार
    0.81
    plätze
    0.71
    прочем
    0.70
     incomplète
    0.69
    第一个
    0.67
    সেই
    0.66
    例子
    0.65
    oje
    0.65
    ه‌ها
    0.65
    Act Density 0.000%

    No Known Activations