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

    Neuronpedia

    INDEX
    Explanations

    adventures

    np_max-act · gemini-2.0-flash

    The neuron never fires—it does not detect any discernible token pattern in these examples.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tongue
    -0.07
     flooding
    -0.06
    	glBind
    -0.06
     scape
    -0.06
     MEMORY
    -0.06
     MONEY
    -0.06
     locks
    -0.06
     plates
    -0.06
     económ
    -0.06
    achine
    -0.06
    POSITIVE LOGITS
     adventures
    0.09
     venture
    0.08
     Adventures
    0.08
     prod
    0.07
     Ventures
    0.07
     Musk
    0.07
    venture
    0.07
    ped
    0.07
     ventures
    0.07
    .series
    0.07
    Act Density 0.022%

    No Known Activations