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

    Neuronpedia

    INDEX
    Explanations

    javascript code tokens like variables, file paths, and functions

    oai_token-act-pair · gemini-2.0-flash

    true/yes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ExtendWith
    -0.75
     للاسماء
    -0.73
    Obrázky
    -0.69
    χρι
    -0.68
    RunWith
    -0.65
     imageNamed
    -0.65
     doubtnut
    -0.64
    Rhestr
    -0.63
    avadoc
    -0.63
     tartalomajánló
    -0.63
    POSITIVE LOGITS
    true
    0.54
     true
    0.52
     Yes
    0.52
    velocityX
    0.49
     [
    0.48
     '
    0.48
     yes
    0.48
    StoreMessageInfo
    0.47
    Yes
    0.46
     YES
    0.46
    Act Density 2.965%

    No Known Activations