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

    Neuronpedia

    INDEX
    Explanations

    punctuation or symbols used to signify sentence boundaries and organization

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

    right, wide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ('=
    -0.24
    postData
    -0.23
    pantalones
    -0.23
     Bedarf
    -0.22
    ubahan
    -0.22
    <
    -0.22
     Persson
    -0.22
     due
    -0.21
     grec
    -0.21
    =('
    -0.20
    POSITIVE LOGITS
    OGND
    0.90
     snippetHide
    0.89
    Autoritní
    0.85
     kasarigan
    0.82
    +#+#
    0.80
    [@BOS@]
    0.77
    <unused17>
    0.77
    <unused42>
    0.77
    <unused14>
    0.77
    <pad>
    0.77
    Act Density 0.001%

    No Known Activations