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

    Neuronpedia

    INDEX
    Explanations

    marketing metrics and business terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کورٹ
    0.39
     Dünya
    0.38
    న్యూ
    0.38
    人类
    0.38
     важней
    0.38
    Unexpected
    0.37
     Same
    0.36
     aynı
    0.36
     fod
    0.36
     insan
    0.36
    POSITIVE LOGITS
    ☞
    0.45
    Ｑ
    0.42
    恨
    0.36
     شويه
    0.36
     déficit
    0.36
    𝑄
    0.36
    wana
    0.36
     لكن
    0.36
     パンツ
    0.35
    ВС
    0.35
    Act Density 0.000%

    No Known Activations