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

    Neuronpedia

    INDEX
    Explanations

    code/punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sidewalks
    -0.07
     chiều
    -0.07
    .:.:.
    -0.07
     dansk
    -0.06
     possibile
    -0.06
    _way
    -0.06
     цьому
    -0.06
     pož
    -0.06
    -plane
    -0.06
     překvap
    -0.06
    POSITIVE LOGITS
    reply
    0.06
     Moran
    0.06
    UTES
    0.06
    -M
    0.06
     twins
    0.06
     urlparse
    0.06
    (rng
    0.06
     HttpSession
    0.06
    whatever
    0.06
     regiment
    0.06
    Act Density 0.000%

    No Known Activations