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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    екар
    -0.06
    olate
    -0.06
    exe
    -0.06
    flows
    -0.06
    -stars
    -0.06
    Kenn
    -0.06
     Give
    -0.06
    Packet
    -0.06
    ToMany
    -0.06
    perms
    -0.06
    POSITIVE LOGITS
     klid
    0.07
     uživatel
    0.07
     เพราะ
    0.07
     blev
    0.07
     ايران
    0.06
    233
    0.06
    context
    0.06
    yi
    0.06
     Tại
    0.06
    	self
    0.06
    Act Density 0.004%

    No Known Activations