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

    Neuronpedia

    INDEX
    Explanations

    Unicode character encodings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Witness
    -0.09
     Seasons
    -0.09
     suspense
    -0.08
     seasons
    -0.08
    χυ
    -0.08
    (glm
    -0.08
    经营
    -0.08
     Runs
    -0.08
    季
    -0.08
    Collateral
    -0.07
    POSITIVE LOGITS
     officielle
    0.09
     repertoire
    0.09
     mappings
    0.09
     번호
    0.09
     Unicode
    0.08
    对应
    0.08
    號
    0.08
     enumeration
    0.08
    Unicode
    0.08
     URI
    0.08
    Act Density 0.010%

    No Known Activations