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

    Neuronpedia

    INDEX
    Explanations

    names and titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _places
    -0.09
     ネ
    -0.07
    FirstChild
    -0.06
     cautious
    -0.06
    _declaration
    -0.06
     زوج
    -0.06
    Ч
    -0.06
    _require
    -0.06
     docs
    -0.06
     advantageous
    -0.06
    POSITIVE LOGITS
    askan
    0.06
     potassium
    0.06
     věn
    0.06
     brilliantly
    0.06
    нат
    0.06
    Sm
    0.06
    ειτουργ
    0.06
    provided
    0.06
     Gly
    0.06
    "),↵
    0.06
    Act Density 0.006%

    No Known Activations