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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric literals (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Mặt
    -0.06
     chops
    -0.06
    负责
    -0.06
     administrator
    -0.06
    overrides
    -0.06
     robotic
    -0.06
     frequencies
    -0.06
    taş
    -0.06
     projection
    -0.06
     ROS
    -0.06
    POSITIVE LOGITS
    pheres
    0.07
     unlink
    0.07
    市
    0.06
    lerce
    0.06
    ışı
    0.06
    gili
    0.06
    (GL
    0.06
     vẫn
    0.06
     Lori
    0.06
    -insert
    0.06
    Act Density 0.680%

    No Known Activations