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

    Neuronpedia

    INDEX
    Explanations

    consumption

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of consumption (eating/drinking) in various forms.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     air
    -0.08
     head
    -0.08
     row
    -0.07
     Aid
    -0.07
     hello
    -0.07
     ilan
    -0.07
     hint
    -0.07
     zig
    -0.07
     battlefield
    -0.07
     legends
    -0.07
    POSITIVE LOGITS
     consumed
    0.12
     consume
    0.11
     consumption
    0.10
    consum
    0.09
     consumes
    0.09
    Consum
    0.08
     Consum
    0.08
     consumo
    0.08
    cem
    0.07
    usu
    0.07
    Act Density 0.016%

    No Known Activations