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

    Neuronpedia

    INDEX
    Explanations

    Braces and colons

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric constants (literal numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    PageIndex
    -0.07
    incinn
    -0.07
     paddingLeft
    -0.07
    Skip
    -0.06
    UFACT
    -0.06
    "]}
    -0.06
    ']}</
    -0.06
     女
    -0.06
     QLabel
    -0.06
     redirected
    -0.06
    POSITIVE LOGITS
    кус
    0.09
    _symbol
    0.08
     biomass
    0.07
     LTE
    0.07
     controversy
    0.07
     Stem
    0.07
     moi
    0.07
    -items
    0.07
     monetary
    0.06
     *
    0.06
    Act Density 0.010%

    No Known Activations