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

    Neuronpedia

    INDEX
    Explanations

    stable conditions, managing schedules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ricing
    0.44
     توصیه
    0.44
    แน่น
    0.44
    setInt
    0.44
     সন্ধ্যায়
    0.43
    𝟕
    0.43
     resorption
    0.43
    ႏ
    0.42
    ولوژی
    0.42
     유형
    0.42
    POSITIVE LOGITS
    :
    0.55
    牛
    0.44
    ：
    0.43
     sque
    0.42
    Iam
    0.42
     لح
    0.42
     creek
    0.41
     f
    0.41
     s
    0.40
     be
    0.39
    Act Density 0.000%

    No Known Activations