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

    Neuronpedia

    INDEX
    Explanations

    the word "floor" and related architectural terms.

    oai_token-act-pair · gemini-2.0-flash

    floor-related terminology

    np_token-act-pair-logits · gpt-4o-mini

    floor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.88
    expandindo
    -0.80
    providedIn
    -0.74
     '\\;'
    -0.73
    didSet
    -0.69
    eably
    -0.67
     estekak
    -0.66
    InitVars
    -0.65
    曖昧さ回避
    -0.65
     createState
    -0.62
    POSITIVE LOGITS
    Linq
    0.49
    BooleanField
    0.44
     train
    0.44
    harmonie
    0.43
    Fed
    0.43
    Dancer
    0.42
    popo
    0.41
     PhpStorm
    0.41
    train
    0.41
    goc
    0.40
    Act Density 1.299%

    No Known Activations