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

    Neuronpedia

    INDEX
    Explanations

    irrigation

    np_max-act · gemini-2.0-flash

    The neuron specifically detects tokens related to irrigation (e.g. “irrigation,” “irrigate,” “Irr”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cctor
    -0.07
    _an
    -0.06
     bombings
    -0.06
     Bailey
    -0.06
     vyb
    -0.06
     Prot
    -0.06
     Trade
    -0.06
     infants
    -0.06
    .listBox
    -0.06
     tempList
    -0.06
    POSITIVE LOGITS
     irrigation
    0.09
     irrig
    0.08
    HAVE
    0.08
     sprink
    0.07
    /theme
    0.07
    .spark
    0.06
    )...
    0.06
    涉
    0.06
    planation
    0.06
     rin
    0.06
    Act Density 0.004%

    No Known Activations