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

    Neuronpedia

    INDEX
    Explanations

    border: none;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    టమి
    0.84
     يوجد
    0.82
    上げる
    0.82
    ilem
    0.81
     Pengembangan
    0.79
     늘
    0.78
    icip
    0.78
    zx
    0.78
     sees
    0.78
    skom
    0.77
    POSITIVE LOGITS
    Compatibility
    0.79
     conservative
    0.67
    Phil
    0.66
    ーフ
    0.65
    निटी
    0.65
    वेलकम
    0.64
    Careers
    0.63
    Conservative
    0.62
    𝘀
    0.61
     compatibility
    0.61
    Act Density 0.001%

    No Known Activations