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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens representing floating-point values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Channel
    -0.07
    est
    -0.07
    ɵ
    -0.06
    leaning
    -0.06
     hubby
    -0.06
     Channel
    -0.06
     fingers
    -0.06
     quoted
    -0.06
     typed
    -0.06
     Bean
    -0.06
    POSITIVE LOGITS
    웅
    0.07
     بیشتری
    0.07
    getParent
    0.06
    �
    0.06
    ('='
    0.06
     �
    0.06
    چه
    0.06
    \xff
    0.06
    <M
    0.06
    _strerror
    0.06
    Act Density 0.062%

    No Known Activations