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

    Neuronpedia

    INDEX
    Explanations

    text related to user input and validation processes in programming

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

    user input prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.70
    featureID
    -0.66
    __':
    -0.65
     snippetHide
    -0.61
    WaitGroup
    -0.59
    XmlAccessorType
    -0.58
    GEBURTSDATUM
    -0.58
    parsedMessage
    -0.56
    berdayakan
    -0.55
     שוליים
    -0.54
    POSITIVE LOGITS
     noDo
    0.43
    حياته
    0.41
    icare
    0.37
     fes
    0.35
     bevor
    0.33
     contra
    0.33
     jo
    0.33
    chtest
    0.33
     indisponible
    0.32
    uxxxx
    0.32
    Act Density 0.006%

    No Known Activations