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

    Neuronpedia

    INDEX
    Explanations

    height

    np_max-act · gemini-2.0-flash

    The neuron is essentially dead—it never activates on any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Sultan
    -0.07
     franc
    -0.07
    лива
    -0.06
     pozdě
    -0.06
    ็นอ
    -0.06
    Sand
    -0.06
     Sand
    -0.06
     GPU
    -0.06
    IntoConstraints
    -0.06
    -user
    -0.06
    POSITIVE LOGITS
     кін
    0.07
     componentDidMount
    0.07
    (height
    0.06
    (long
    0.06
     Hispanics
    0.06
     церков
    0.06
     Александ
    0.06
    öyle
    0.06
     licences
    0.06
    esper
    0.06
    Act Density 0.002%

    No Known Activations