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

    Neuronpedia

    INDEX
    Explanations

    it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     executable
    0.18
    を使用
    0.17
     radiated
    0.16
     acacia
    0.16
    ኒ
    0.16
     コン
    0.15
     aldığı
    0.15
     magenta
    0.15
     alc
    0.15
     emits
    0.15
    POSITIVE LOGITS
    aworld
    0.16
     особенно
    0.15
    án
    0.15
     memang
    0.15
     grieving
    0.14
    izzle
    0.14
     खासकर
    0.14
     சம்பந்த
    0.14
     plantea
    0.14
     wary
    0.14
    Act Density 0.843%

    No Known Activations