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
     needles
    -0.07
    "Now
    -0.07
     fried
    -0.06
    Scheduled
    -0.06
     ног
    -0.06
     Mirage
    -0.06
     ва
    -0.06
     forfeiture
    -0.06
     dernier
    -0.06
     fø
    -0.06
    POSITIVE LOGITS
    пня
    0.07
    isodes
    0.06
     sadly
    0.06
     atom
    0.06
    Ш
    0.06
    -Б
    0.06
    vest
    0.06
     ترجمه
    0.06
    剧
    0.06
     asym
    0.06
    Act Density 0.028%

    No Known Activations