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

    Neuronpedia

    INDEX
    Explanations

    tables and examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ിലാ
    0.43
     spongy
    0.43
     future
    0.42
     পাকিস্তানীদের
    0.42
     المستقبل
    0.42
     inev
    0.40
     کوي
    0.40
     ダイ
    0.40
     phá
    0.40
    ूला
    0.39
    POSITIVE LOGITS
    iend
    0.43
    Emple
    0.42
    ENANCE
    0.40
    persons
    0.40
    ving
    0.38
    cik
    0.38
     evidences
    0.38
    ®
    0.38
     Gant
    0.38
    Examples
    0.37
    Act Density 0.001%

    No Known Activations