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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of organizational membership (e.g. “member of the … Party”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     anál
    -0.08
     เ�
    -0.07
     inclus
    -0.07
    .hadoop
    -0.07
    IVING
    -0.07
    Allocation
    -0.07
     heuristic
    -0.07
     gap
    -0.06
    .interface
    -0.06
    ctest
    -0.06
    POSITIVE LOGITS
     don
    0.07
    elapsed
    0.06
     smlouvy
    0.06
     ослож
    0.06
    ่ก
    0.06
    locator
    0.05
     violin
    0.05
    ETH
    0.05
    イス
    0.05
    امي
    0.05
    Act Density 0.014%

    No Known Activations