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

    Neuronpedia

    INDEX
    Explanations

    hyphens

    np_max-act · gemini-2.0-flash

    The neuron fires on numerical measurements (especially decimal-point numbers specifying dimensions or distances).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _sync
    -0.07
    utorial
    -0.07
     Ni
    -0.06
     respectively
    -0.06
     Gamma
    -0.06
    remaining
    -0.06
    스템
    -0.06
    ิโล
    -0.06
    principal
    -0.06
     Broadcasting
    -0.06
    POSITIVE LOGITS
     shootings
    0.07
    �
    0.06
    .MILLISECONDS
    0.06
     гиб
    0.06
     "?"
    0.06
     chứ
    0.06
     �
    0.06
    _PHP
    0.06
     말을
    0.06
    �
    0.06
    Act Density 0.021%

    No Known Activations