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

    Neuronpedia

    INDEX
    Explanations

    rf

    np_max-act · gemini-2.0-flash

    The neuron never activates on any tokens, so it effectively doesn’t detect or respond to any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     мала
    -0.07
     �
    -0.07
    찰
    -0.06
     flirting
    -0.06
     pistols
    -0.06
     означа
    -0.06
     угод
    -0.06
    ãng
    -0.06
     आ
    -0.06
    나요
    -0.06
    POSITIVE LOGITS
    (component
    0.07
    (media
    0.07
    Pet
    0.07
     retrieved
    0.06
    Panel
    0.06
    _rep
    0.06
     getState
    0.06
     BroadcastReceiver
    0.06
     CH
    0.06
    Natural
    0.06
    Act Density 0.001%

    No Known Activations