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

    Neuronpedia

    INDEX
    Explanations

    Concise descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belong
    -0.07
     grandparents
    -0.07
     BorderLayout
    -0.07
     İşte
    -0.06
    ющего
    -0.06
     crosses
    -0.06
    ,"
    -0.06
    (close
    -0.06
     placements
    -0.06
    ^^
    -0.06
    POSITIVE LOGITS
    _low
    0.07
    _marshaled
    0.06
     voyeur
    0.06
     itertools
    0.06
    sher
    0.06
     тисяч
    0.06
    COMP
    0.06
    ić
    0.06
    unwrap
    0.06
    bo
    0.06
    Act Density 0.018%

    No Known Activations