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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shipment
    -0.08
    -keys
    -0.07
    elon
    -0.07
     fungus
    -0.07
    ipt
    -0.06
    uct
    -0.06
     impatient
    -0.06
     lime
    -0.06
    岡
    -0.06
     birds
    -0.06
    POSITIVE LOGITS
     ikt
    0.07
     рух
    0.06
    _seconds
    0.06
    ίνη
    0.06
    öz
    0.06
    ")),
    0.06
     disclosing
    0.06
     belg
    0.06
    CLK
    0.06
     جز
    0.06
    Act Density 0.086%

    No Known Activations