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

    Neuronpedia

    INDEX
    Explanations

    'd

    np_max-act · gemini-2.0-flash

    This neuron detects the auxiliary “had,” highlighting past‐perfect constructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    experimental
    -0.06
    ixe
    -0.06
     unterstüt
    -0.06
    quire
    -0.06
    .TEXT
    -0.06
    ользоват
    -0.06
     forfeiture
    -0.06
    ft
    -0.06
     PM
    -0.06
    Actualizar
    -0.06
    POSITIVE LOGITS
     stemming
    0.07
     href
    0.06
    ’d
    0.06
     amphib
    0.06
     leather
    0.06
    redo
    0.06
     Satoshi
    0.06
    рад
    0.06
     Ã
    0.06
     Medal
    0.06
    Act Density 0.043%

    No Known Activations