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

    Neuronpedia

    INDEX
    Explanations

    code and programming-related syntax

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

    programming and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.93
     ſta
    -0.90
    ſelf
    -0.88
    featureID
    -0.87
     ſch
    -0.85
     queſta
    -0.81
     faſt
    -0.81
     للمعارف
    -0.80
     ſte
    -0.79
     disambiguazione
    -0.75
    POSITIVE LOGITS
     aplicable
    0.36
     prohibido
    0.34
     montañas
    0.33
     Begleitung
    0.30
    .
    0.30
     acuerdos
    0.30
     llamadas
    0.28
     Zusch
    0.28
     from
    0.28
     Ciencias
    0.28
    Act Density 0.003%

    No Known Activations