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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron remains inactive (zero response) for all tokens, i.e. it does not detect or respond to any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    єї
    -0.07
     Rigidbody
    -0.07
    ूचन
    -0.06
     svých
    -0.06
     svém
    -0.06
     need
    -0.06
     accused
    -0.06
    study
    -0.06
    gMaps
    -0.06
     accordingly
    -0.06
    POSITIVE LOGITS
     Smithsonian
    0.07
     compos
    0.07
    ист
    0.07
    로그
    0.06
     окра
    0.06
     chromat
    0.06
    Nut
    0.06
     conversions
    0.06
    _IS
    0.06
     arteries
    0.06
    Act Density 0.018%

    No Known Activations