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

    Neuronpedia

    INDEX
    Explanations

    elements related to HTML document structure and metadata

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

    HTML stylesheet links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -1.10
    出版年
    -1.10
     Мексичка
    -1.09
     }}"></
    -1.06
     Signalez
    -1.06
    %"),
    -0.99
    OGND
    -0.98
    abestanden
    -0.97
    %")
    -0.96
     autorytatywna
    -0.93
    POSITIVE LOGITS
    .
    0.82
    ↵↵
    0.66
    ,
    0.63
    ↵
    0.49
    ;
    0.47
    !
    0.46
     with
    0.46
     the
    0.43
    ?
    0.43
     (
    0.43
    Act Density 0.023%

    No Known Activations