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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens representing non-integer (decimal or floating-point) values.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ulmuş
    -0.07
     الخامسة
    -0.07
    BCM
    -0.07
     dams
    -0.07
     тоб
    -0.07
     exiting
    -0.06
     poets
    -0.06
     bütün
    -0.06
    Ki
    -0.06
    通り
    -0.06
    POSITIVE LOGITS
     půl
    0.06
    :aload
    0.06
    _CHARSET
    0.06
    =count
    0.06
    %@",
    0.06
    NSArray
    0.06
    _cate
    0.06
    ])]
    0.06
     Tarif
    0.06
    monton
    0.06
    Act Density 0.029%

    No Known Activations