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
     Cloud
    -0.06
    .Stretch
    -0.06
     ABI
    -0.06
    misc
    -0.06
    906
    -0.06
     CID
    -0.06
    	br
    -0.06
     sep
    -0.06
    	DBG
    -0.06
    пер
    -0.06
    POSITIVE LOGITS
    "Yeah
    0.06
    doctor
    0.06
     parody
    0.06
    Concat
    0.06
    отя
    0.06
    _BS
    0.06
    _procs
    0.06
    نتی
    0.06
     relent
    0.06
    장이
    0.06
    Act Density 0.002%

    No Known Activations