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

    Neuronpedia

    INDEX
    Explanations

    html

    np_max-act · gemini-2.0-flash

    The neuron activates on standalone numeric tokens (single-digit numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    zes
    -0.07
    ி
    -0.06
    �
    -0.06
    _to
    -0.06
     lành
    -0.06
    strstr
    -0.06
    isiert
    -0.06
    чини
    -0.06
    izado
    -0.06
    하면서
    -0.06
    POSITIVE LOGITS
    VA
    0.07
     Port
    0.07
    拟
    0.07
     specifics
    0.07
    nie
    0.07
     bott
    0.06
     inner
    0.06
     ceramics
    0.06
    >(()
    0.06
     triangular
    0.06
    Act Density 0.024%

    No Known Activations