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

    Neuronpedia

    INDEX
    Explanations

    fermentation

    np_max-act · gemini-2.0-flash

    The neuron is tuned to pick out references to fermentation, activating on forms of the “ferment”/“fermentation” root.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unlocked
    -0.07
     グ
    -0.06
     Biol
    -0.06
    ========↵
    -0.06
    -key
    -0.06
    reshold
    -0.06
     hole
    -0.06
    books
    -0.06
    Ｃ
    -0.06
     Playboy
    -0.06
    POSITIVE LOGITS
     ferment
    0.10
     fermentation
    0.09
     fermented
    0.09
     lửa
    0.07
    MLElement
    0.07
     eman
    0.07
    ething
    0.07
     ecommerce
    0.06
    enta
    0.06
     ceremony
    0.06
    Act Density 0.002%

    No Known Activations