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

    Neuronpedia

    INDEX
    Explanations

    language describing expertise

    oai_token-act-pair · gemini-2.0-flash

    Experts/specialists

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    참고
    -0.77
    __':
    -0.75
    KommentareTeilen
    -0.69
    __":
    -0.65
    AndEndTag
    -0.63
    TagMode
    -0.61
     ujednoznacz
    -0.60
    PostInfinity
    -0.59
    SourceChecksum
    -0.58
    setVerticalGroup
    -0.57
    POSITIVE LOGITS
     experts
    1.84
     expert
    1.73
    Experts
    1.50
     Experts
    1.49
     specialists
    1.45
    expert
    1.43
    experts
    1.41
     expertos
    1.40
     specialist
    1.38
     Expert
    1.37
    Act Density 0.666%

    No Known Activations