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

    Neuronpedia

    INDEX
    Explanations

    tech companies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shorten
    -0.08
    _unsigned
    -0.08
     얼마
    -0.08
     Uns
    -0.08
    ieß
    -0.07
     shortening
    -0.07
    _SHORT
    -0.07
     unsigned
    -0.07
    annar
    -0.07
    Unsigned
    -0.07
    POSITIVE LOGITS
     prolific
    0.11
     dominates
    0.10
     dominate
    0.10
    人気
    0.10
     dominant
    0.09
     pioneered
    0.09
    popular
    0.09
     dominance
    0.09
     ubiquitous
    0.09
     famous
    0.09
    Act Density 0.051%

    No Known Activations