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

    Neuronpedia

    INDEX
    Explanations

    parameter

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of model parameters—especially free or phenomenological parameters—in scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .!
    -0.07
    欢
    -0.06
     conveying
    -0.06
    normally
    -0.06
    -0.06
    _generic
    -0.06
    _through
    -0.06
    ¡
    -0.06
     Š
    -0.06
    (ids
    -0.06
    POSITIVE LOGITS
    .ForEach
    0.07
    	elsif
    0.06
     needle
    0.06
     choix
    0.06
    .error
    0.06
    782
    0.06
     education
    0.06
    .scatter
    0.06
     DEVICE
    0.06
     finan
    0.06
    Act Density 0.014%

    No Known Activations