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

    Neuronpedia

    INDEX
    Explanations

    punctuation and spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catalog
    -0.08
     catalogs
    -0.08
     zuwa
    -0.08
     reprodu
    -0.07
    entic
    -0.07
     candies
    -0.07
    Fonte
    -0.07
    анада
    -0.07
     samples
    -0.07
     kano
    -0.07
    POSITIVE LOGITS
     leftover
    0.09
    missing
    0.09
     dangling
    0.09
     awkward
    0.09
     કારણે
    0.08
    -extra
    0.08
    遗漏
    0.08
     제거
    0.08
    Oops
    0.08
    211
    0.08
    Act Density 0.010%

    No Known Activations