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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =d
    -0.06
     какие
    -0.06
    買
    -0.06
     Kern
    -0.06
    (金
    -0.06
     Mental
    -0.06
     أغ
    -0.06
    _ALERT
    -0.06
    fm
    -0.06
    рович
    -0.06
    POSITIVE LOGITS
     recognizer
    0.07
    (""));↵
    0.07
    ウン
    0.07
    <string
    0.06
    урс
    0.06
    missions
    0.06
     Saskatchewan
    0.06
     equipments
    0.06
    isset
    0.06
     orbit
    0.06
    Act Density 0.002%

    No Known Activations