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

    Neuronpedia

    INDEX
    Explanations

    academic papers and machine learning concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChatGPT
    0.43
    OCS
    0.39
     Stanley
    0.38
    WS
    0.38
    [...]
    0.37
    더라구요
    0.37
     ந
    0.37
    TikTok
    0.37
     micrograph
    0.36
    पीएफ
    0.36
    POSITIVE LOGITS
    ܛ
    0.44
    檗
    0.43
    ಳ
    0.42
    ುಂಬ
    0.39
     विद्यार्थ
    0.38
    ীম
    0.38
     кислоты
    0.38
     तल
    0.38
     $_
    0.38
    ุป
    0.37
    Act Density 0.002%

    No Known Activations