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

    Neuronpedia

    INDEX
    Explanations

    sequences or combinations of numbers and code structure

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

    Characters followed by digits and colons

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >--}}
    -0.60
     hinweg
    -0.52
     Uli
    -0.52
    washer
    -0.51
     يتيمه
    -0.51
    metz
    -0.50
    esco
    -0.49
    ibly
    -0.49
    nix
    -0.48
    urfs
    -0.48
    POSITIVE LOGITS
    RenderAtEndOf
    0.67
    TagMode
    0.63
    UnusedPrivate
    0.55
    ExecuteReader
    0.54
    ReusableCell
    0.54
    fxml
    0.52
     defaultstate
    0.52
     jScrollPane
    0.52
     TextAppearance
    0.51
    oa̍t
    0.48
    Act Density 0.158%

    No Known Activations