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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric tokens representing decimal‐fraction values (floating‐point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     verbess
    -0.06
     거야
    -0.06
    -but
    -0.06
    answer
    -0.06
     Consumption
    -0.06
     aprove
    -0.06
    DMA
    -0.06
    .the
    -0.06
    .bn
    -0.06
     locking
    -0.06
    POSITIVE LOGITS
    (QWidget
    0.08
    LineEdit
    0.07
     onFailure
    0.07
    .QLabel
    0.07
     Shops
    0.07
     QPushButton
    0.07
     Islanders
    0.07
     ulus
    0.07
    (atom
    0.06
    .routes
    0.06
    Act Density 0.002%

    No Known Activations