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

    Neuronpedia

    INDEX
    Explanations

    Other languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ans
    -0.07
     Broadcast
    -0.07
     town
    -0.07
     Understanding
    -0.07
     nums
    -0.07
    	ans
    -0.06
     understanding
    -0.06
    +[
    -0.06
     meddling
    -0.06
     PCIe
    -0.06
    POSITIVE LOGITS
     Jeg
    0.07
    _constant
    0.06
    �
    0.06
     LIABLE
    0.06
    uluk
    0.06
    Ậ
    0.06
    NotNil
    0.06
     Mev
    0.06
     donations
    0.06
    ",$
    0.06
    Act Density 0.075%

    No Known Activations