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

    Neuronpedia

    INDEX
    Explanations

    matter

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “matter” (and to a lesser extent “energy”), especially in physics‐definition passages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    От
    -0.07
    ยาย
    -0.07
     dzieci
    -0.07
    	bus
    -0.07
    _calls
    -0.07
     mejores
    -0.07
    >
↵
↵
    -0.07
     obligations
    -0.06
    fds
    -0.06
     piece
    -0.06
    POSITIVE LOGITS
    Installer
    0.07
     matter
    0.07
    -party
    0.07
     représ
    0.07
    .Itoa
    0.06
    _METADATA
    0.06
     altered
    0.06
     Athen
    0.06
    .itemId
    0.06
     Featured
    0.06
    Act Density 0.005%

    No Known Activations