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

    Neuronpedia

    INDEX
    Explanations

    naturally/natural

    np_max-act · gemini-2.0-flash

    This neuron responds to descriptive terms that emphasize a substance’s natural occurrence or intrinsic properties (e.g. “naturally,” “occurring,” “secreted”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     simulation
    -0.07
     simulations
    -0.07
    �
    -0.07
     Greater
    -0.06
     Gus
    -0.06
     Operation
    -0.06
    DOWNLOAD
    -0.06
    zy
    -0.06
    _rat
    -0.06
     tutors
    -0.06
    POSITIVE LOGITS
     tamamen
    0.07
     eser
    0.07
     customized
    0.07
    -overlay
    0.06
     "?
    0.06
     ray
    0.06
     امیر
    0.06
    lint
    0.06
     volupt
    0.06
     intra
    0.06
    Act Density 0.024%

    No Known Activations