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

    Neuronpedia

    INDEX
    Explanations

    Attaining or receiving

    np_max-act · gemini-2.0-flash

    This neuron is essentially “dead”: it never activates on any tokens and thus does not detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SHR
    -0.06
     зависимости
    -0.06
    rah
    -0.06
    evenodd
    -0.06
    扶
    -0.06
    \Route
    -0.06
    .strftime
    -0.06
     pedestal
    -0.06
     تعداد
    -0.06
    globals
    -0.06
    POSITIVE LOGITS
    etc
    0.07
    679
    0.07
    .Layer
    0.06
     reprodu
    0.06
    cow
    0.06
     metaData
    0.06
     stren
    0.06
     ACPI
    0.06
     wol
    0.06
    ùi
    0.06
    Act Density 0.120%

    No Known Activations