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
     Heads
    -0.07
    Bus
    -0.07
    hours
    -0.06
    -outs
    -0.06
     bricks
    -0.06
     Simon
    -0.06
     Sunshine
    -0.06
     chilled
    -0.06
     unicorn
    -0.06
    itas
    -0.06
    POSITIVE LOGITS
    ुत
    0.07
     """
↵
↵
    0.06
     dob
    0.06
    +A
    0.06
     توسعه
    0.06
     elgg
    0.06
    .cols
    0.06
     Enums
    0.06
    brities
    0.06
    .priority
    0.06
    Act Density 0.098%

    No Known Activations