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

    Neuronpedia

    INDEX
    Explanations

    programming constructs and object definitions

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

    programming, math, and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.69
     beginnetje
    -0.66
    rungsseite
    -0.66
    énario
    -0.64
     >",
    -0.57
    ロウィン
    -0.56
    homonymie
    -0.56
    OGND
    -0.56
    UnusedPrivate
    -0.55
    Билгалдахарш
    -0.55
    POSITIVE LOGITS
    которые
    0.58
    withstanding
    0.54
     autorytatywna
    0.44
    oltre
    0.43
    oredCriteria
    0.42
    //
    0.40
     nakalista
    0.38
     nonUne
    0.37
    ofthe
    0.35
    quiries
    0.33
    Act Density 0.299%

    No Known Activations