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

    Neuronpedia

    INDEX
    Explanations

    Satellites

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on tokens in the opening descriptive section of a spacecraft or satellite article—particularly on the satellite’s name and its technical and mission‐related details.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Mu
    -0.07
    Bed
    -0.07
     surrendered
    -0.06
     جديدة
    -0.06
    translator
    -0.06
    apı
    -0.06
     drastically
    -0.06
    laden
    -0.06
     formally
    -0.06
     running
    -0.06
    POSITIVE LOGITS
    	Common
    0.07
     Outputs
    0.06
     реб
    0.06
    _ASSERT
    0.06
    mutex
    0.06
    compat
    0.06
    .Tipo
    0.06
     preserve
    0.06
     juegos
    0.06
     artículo
    0.06
    Act Density 0.009%

    No Known Activations