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

    Neuronpedia

    INDEX
    Explanations

    passage or age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leurs
    -0.07
     总
    -0.06
     老
    -0.06
    _js
    -0.06
     ضر
    -0.06
    老
    -0.06
    rparr
    -0.06
     repr
    -0.06
     elected
    -0.06
    总
    -0.06
    POSITIVE LOGITS
     passage
    0.19
     Passage
    0.15
     passages
    0.14
     voyage
    0.09
    (space
    0.09
    λογή
    0.08
     transmission
    0.08
    age
    0.08
    nze
    0.08
    _attachment
    0.08
    Act Density 0.004%

    No Known Activations