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

    Neuronpedia

    INDEX
    Explanations

    quantitative data or numerical information

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

    Phone numbers, especially area codes

    np_acts-logits-general · gemini-2.0-flash

    untold suffering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.76
     BnF
    -0.50
    AddHtmlAttribute
    -0.49
     id
    -0.49
    WriteAttribute
    -0.49
    otyp
    -0.48
     most
    -0.47
     super
    -0.47
     recor
    -0.45
    Marshaller
    -0.45
    POSITIVE LOGITS
     tartalomajánló
    0.83
    AsUp
    0.79
     Grüsse
    0.79
     autorytatywna
    0.69
     hjemmeside
    0.68
     courriel
    0.67
     étanche
    0.67
     fermés
    0.66
     dourada
    0.66
     imprensa
    0.65
    Act Density 0.051%

    No Known Activations