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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on numeric measurement tokens (especially floating‐point values) in the experimental/crystallographic data.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     passes
    -0.06
     клад
    -0.06
    _PARAMS
    -0.06
     amber
    -0.06
    ,axis
    -0.06
    imleri
    -0.06
     basin
    -0.06
     awaken
    -0.06
     refs
    -0.06
    _channel
    -0.06
    POSITIVE LOGITS
    almost
    0.07
     Bes
    0.07
     capturing
    0.07
    _Camera
    0.07
     potrze
    0.07
    vertis
    0.06
     Senator
    0.06
     Reve
    0.06
    Experts
    0.06
     When
    0.06
    Act Density 0.001%

    No Known Activations