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

    Neuronpedia

    INDEX
    Explanations

    context is crucial

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lijk
    2.24
    ipa
    2.22
     dets
    2.11
    雳
    2.08
    дою
    2.06
    æss
    2.06
    डिशा
    2.06
    িতার
    2.02
    ırı
    2.02
    alsey
    2.01
    POSITIVE LOGITS
    ⎦
    2.72
    s
    2.66
    க்கள்
    2.62
    ات
    2.45
    sle
    2.44
    emption
    2.40
    ொண்டு
    2.39
    MenuStrip
    2.35
    ים
    2.33
    ের
    2.28
    Act Density 0.887%

    No Known Activations