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

    Neuronpedia

    INDEX
    Explanations

    Bust words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	node
    -0.07
    illaume
    -0.07
    觀
    -0.07
     телеф
    -0.07
     воздух
    -0.07
    lige
    -0.07
     станд
    -0.07
     press
    -0.07
     adel
    -0.06
     doch
    -0.06
    POSITIVE LOGITS
     bust
    0.18
     Bust
    0.17
     busted
    0.11
    busters
    0.09
    ust
    0.09
    UST
    0.08
    uster
    0.08
    spir
    0.08
    usting
    0.07
     rust
    0.07
    Act Density 0.002%

    No Known Activations