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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric literals with decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    678
    -0.08
    Fac
    -0.07
     "("
    -0.06
     emergencies
    -0.06
    とした
    -0.06
     ident
    -0.06
     unbearable
    -0.06
     validar
    -0.06
    306
    -0.06
     ach
    -0.06
    POSITIVE LOGITS
    níků
    0.07
    _nth
    0.07
    ConfigureAwait
    0.07
    û
    0.06
    лена
    0.06
    uat
    0.06
     (@
    0.06
    ó
    0.06
    إ
    0.06
    command
    0.06
    Act Density 0.024%

    No Known Activations