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

    Neuronpedia

    INDEX
    Explanations

    Process lifecycles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -à
    -0.08
     wym
    -0.07
    urop
    -0.07
    ,list
    -0.07
    signup
    -0.07
     Verständ
    -0.07
     […
    -0.07
    ovirus
    -0.07
    _signature
    -0.07
    /or
    -0.07
    POSITIVE LOGITS
     thereafter
    0.14
     subsequent
    0.13
     ongoing
    0.13
     дальнейшем
    0.12
     지속
    0.12
     póź
    0.11
     afterwards
    0.11
     Subse
    0.11
     afterward
    0.11
     പിന്നീട്
    0.11
    Act Density 0.167%

    No Known Activations