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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numeric literals (decimal numbers) in technical text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Hello
    -0.07
    Receive
    -0.06
     Hospitals
    -0.06
    ývá
    -0.06
     brunch
    -0.06
    리그
    -0.06
    _robot
    -0.06
     خلال
    -0.06
     Irr
    -0.06
    Hello
    -0.06
    POSITIVE LOGITS
    
    0.06
     Adjust
    0.06
     mAdapter
    0.06
    .OrdinalIgnoreCase
    0.06
    Wunused
    0.06
    :::|
    0.06
     {}
↵
    0.06
    NaN
    0.06
    ากาศ
    0.06
     अ
    0.06
    Act Density 0.079%

    No Known Activations