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

    Neuronpedia

    INDEX
    Explanations

    references to specific technical terms and abbreviations related to scientific or programming contexts

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

    credit card numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -0.68
    featureID
    -0.68
    الإنجليزية
    -0.63
     مشين
    -0.62
    BRL
    -0.58
    новниш
    -0.57
    USR
    -0.56
    XXII
    -0.56
    UPA
    -0.56
    PREFERRED
    -0.56
    POSITIVE LOGITS
     feroit
    0.63
     desmotivaciones
    0.59
     víctimas
    0.57
    周泽
    0.57
    QUENCE
    0.55
     auroit
    0.54
     dieux
    0.54
     pouvoit
    0.53
    cartão
    0.52
     Normdatei
    0.52
    Act Density 0.208%

    No Known Activations