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

    Neuronpedia

    INDEX
    Explanations

    grapes

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of grapes and closely related vine/vineyard terms (e.g., “grape,” “vine,” “vineyards”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     SD
    -0.07
     anomaly
    -0.06
     UI
    -0.06
     buffer
    -0.06
    Locker
    -0.06
    _errno
    -0.06
    _IOCTL
    -0.06
    dbuf
    -0.06
     Koh
    -0.06
    Outlined
    -0.05
    POSITIVE LOGITS
     grape
    0.14
     grapes
    0.14
     Grape
    0.13
     vine
    0.10
    �
    0.09
     vines
    0.09
     Vine
    0.08
    has
    0.07
     drops
    0.07
     svou
    0.07
    Act Density 0.003%

    No Known Activations