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

    Neuronpedia

    INDEX
    Explanations

    structure and formatting changes in text, such as special characters and non-text elements

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

    Text dividers or separators

    np_acts-logits-general · gemini-2.0-flash

    separators or delimitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FetchType
    -0.90
    setVerticalGroup
    -0.89
    NUMX
    -0.80
    principalColumn
    -0.80
    Hauptartikel
    -0.76
     mergeFrom
    -0.73
    featureID
    -0.73
    ]")]
    -0.73
    MockBean
    -0.72
     <=",
    -0.72
    POSITIVE LOGITS
    ↵↵
    0.69
    begin
    0.49
    oOo
    0.48
    end
    0.46
    snip
    0.46
    ↵↵↵
    0.45
    <eos>
    0.45
    oo
    0.44
    Ends
    0.43
    分割
    0.43
    Act Density 0.462%

    No Known Activations