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

    Neuronpedia

    INDEX
    Explanations

    references to space or areas in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "space" or related terms

    np_acts-logits-general · gemini-2.0-flash

    space followed by specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.80
     <<<<<<<<<<<<<<
    -0.74
    ="#">
    -0.69
    STEL
    -0.68
    IsPostBack
    -0.64
    intios
    -0.63
    OwnProperty
    -0.62
    )]$
    -0.62
    setVerticalGroup
    -0.61
    memoized
    -0.60
    POSITIVE LOGITS
     spaces
    0.89
     space
    0.82
     SPACE
    0.81
     Space
    0.77
    spaces
    0.77
    Spaces
    0.76
    SPACE
    0.73
     Spaces
    0.72
    Space
    0.68
    y
    0.61
    Act Density 0.058%

    No Known Activations