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

    Neuronpedia

    INDEX
    Explanations

    words beginning with "con" or containing "ject", "junct", or "direct"

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.62
     مرئيه
    -0.59
    SourceChecksum
    -0.56
     otomatig
    -0.53
     Dominus
    -0.52
     indeterminate
    -0.50
    NewUrlParser
    -0.50
     traced
    -0.49
     tattoo
    -0.48
    random
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.63
    GEBURTSDATUM
    0.61
    تقاوى
    0.60
     незавершена
    0.51
    CTIONS
    0.50
    complexType
    0.49
    CppMethod
    0.48
    ção
    0.48
    ções
    0.48
    ctl
    0.48
    Act Density 0.861%

    No Known Activations