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

    Neuronpedia

    INDEX
    Explanations

    code-related terms and technical language

    oai_token-act-pair · gemini-2.0-flash

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المعرف
    -0.54
    ValueGeneration
    -0.54
     gyhoeddwyd
    -0.49
     tivesse
    -0.49
     TeV
    -0.48
     sottile
    -0.46
    昂
    -0.45
    ίος
    -0.44
    יין
    -0.44
     costly
    -0.44
    POSITIVE LOGITS
    клопе
    0.70
    bootstrapcdn
    0.63
     mergeFrom
    0.57
    ∮
    0.57
    Geplaatst
    0.55
    IsContent
    0.54
    afel
    0.53
     Gazetteer
    0.52
    erm
    0.51
     ihop
    0.50
    Act Density 7.119%

    No Known Activations