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

    Neuronpedia

    INDEX
    Explanations

    specific formatting elements and syntax structures in code or structured data

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

    email addresses and code identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.87
     Италијани
    -0.69
    Tikang
    -0.68
    rungsseite
    -0.63
    ロウィン
    -0.59
     beginnetje
    -0.56
    :✨
    -0.56
     يتيمه
    -0.55
    Rujuakan
    -0.54
     Geſch
    -0.53
    POSITIVE LOGITS
    cyd
    0.41
    MigrationBuilder
    0.40
     Az
    0.38
     орга
    0.38
     Papa
    0.38
    dd
    0.37
    indd
    0.36
    dojo
    0.36
    inflater
    0.36
    matches
    0.36
    Act Density 0.061%

    No Known Activations