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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    診
    -0.07
    ating
    -0.07
     /^\
    -0.07
    μοί
    -0.06
    yst
    -0.06
    NavigationBar
    -0.06
    doctrine
    -0.06
     těl
    -0.06
    (conv
    -0.06
    thed
    -0.06
    POSITIVE LOGITS
    _que
    0.07
     whe
    0.06
    (col
    0.06
    	ar
    0.06
     relied
    0.06
     Adidas
    0.06
    BUG
    0.06
     ","↵
    0.06
    ="<<
    0.06
     f
    0.06
    Act Density 0.009%

    No Known Activations