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

    Neuronpedia

    INDEX
    Explanations

    directional

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any of the input tokens, indicating it is effectively inactive or unresponsive.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     manuscript
    -0.07
     fragmented
    -0.06
     Range
    -0.06
    rites
    -0.06
    Luke
    -0.06
     apart
    -0.06
    CellStyle
    -0.06
    त
    -0.06
     Scout
    -0.05
     weg
    -0.05
    POSITIVE LOGITS
    irectional
    0.07
    로부터
    0.07
    čního
    0.07
     devastating
    0.07
     Takım
    0.06
    .transfer
    0.06
    ikt
    0.06
    願
    0.06
    ßerdem
    0.06
     yılında
    0.06
    Act Density 0.001%

    No Known Activations