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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to specific numeric or measurement criteria

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

    last or final

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.61
    🟨
    -0.53
    ähteet
    -0.52
    SequentialGroup
    -0.52
     Spreadsheet
    -0.51
     panela
    -0.50
    alakip
    -0.49
    arangay
    -0.48
     caneca
    -0.48
     createState
    -0.48
    POSITIVE LOGITS
     última
    1.34
     último
    1.27
     últimos
    1.24
     dernière
    1.23
     dernier
    1.23
     ultimi
    1.20
    ultimo
    1.20
     dernières
    1.19
    ultima
    1.15
     last
    1.14
    Act Density 0.003%

    No Known Activations