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

    Neuronpedia

    INDEX
    Explanations

    carve

    np_max-act · gemini-2.0-flash

    The neuron activates on words referring to sculptural activities—especially carving or sculpting.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (dist
    -0.08
     mish
    -0.07
    ientos
    -0.07
    olumbia
    -0.07
    icias
    -0.07
    .volley
    -0.06
     попада
    -0.06
    dbContext
    -0.06
     hur
    -0.06
    スポ
    -0.06
    POSITIVE LOGITS
     carved
    0.12
     carve
    0.10
     carving
    0.09
     Weber
    0.08
     Carpenter
    0.07
     ESV
    0.07
     Garmin
    0.07
     Navy
    0.07
     Marble
    0.07
     Reactive
    0.07
    Act Density 0.007%

    No Known Activations