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

    Neuronpedia

    INDEX
    Explanations

    options and steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conex
    0.44
     aanv
    0.44
     poet
    0.43
     فوټبال
    0.43
    ەل
    0.42
     아이
    0.41
    textColor
    0.41
     velvety
    0.41
     oh
    0.41
     cuddle
    0.41
    POSITIVE LOGITS
    olim
    0.49
     arresting
    0.44
    मध्ये
    0.42
    俭
    0.42
     satta
    0.42
    বিশেষ
    0.41
    0.41
    jaan
    0.41
    werte
    0.41
    jah
    0.41
    Act Density 0.101%

    No Known Activations