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

    Neuronpedia

    INDEX
    Explanations

    key-value pairings in configuration or programming code

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

    assignment or code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.80
     <>",
    -0.74
    featureID
    -0.74
     سكانية
    -0.68
    RenderAtEndOf
    -0.68
     snippetHide
    -0.65
    DockStyle
    -0.63
    AnchorStyles
    -0.63
    хьтан
    -0.63
     дописавши
    -0.61
    POSITIVE LOGITS
    The
    0.47
    That
    0.46
    What
    0.46
     auroit
    0.43
     étoit
    0.42
    that
    0.41
     pouvoit
    0.41
     berarti
    0.40
    what
    0.40
     what
    0.39
    Act Density 0.046%

    No Known Activations