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

    Neuronpedia

    INDEX
    Explanations

    seemingly random isolated numbers in code

    oai_token-act-pair · gemini-2.0-flash

    Code, equations, identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nine
    -0.72
     eighth
    -0.71
     ninth
    -0.69
     eight
    -0.66
     seventh
    -0.64
     Eight
    -0.63
    八
    -0.62
     delapan
    -0.62
     Nine
    -0.62
    8
    -0.62
    POSITIVE LOGITS
    AndroidJUnit
    0.66
    endphp
    0.66
    bootstrapcdn
    0.61
     فريبيس
    0.59
     gyhoeddwyd
    0.59
    RenderAtEndOf
    0.58
     continúas
    0.58
    aculture
    0.56
    ScopeManager
    0.55
    FormBuilder
    0.54
    Act Density 3.593%

    No Known Activations