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

    Neuronpedia

    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash

    This neuron fires on continuous narrative or descriptive prose—long stretches of running text rather than isolated tokens or markup.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ابه
    -0.07
    yle
    -0.06
    Integrated
    -0.06
    .isAuthenticated
    -0.06
     comercial
    -0.06
    ---------------↵
    -0.06
    �
    -0.06
    specified
    -0.06
     :\
    -0.06
    emption
    -0.06
    POSITIVE LOGITS
     gets
    0.07
     Mechanics
    0.07
    Основ
    0.06
     Kin
    0.06
    oliday
    0.06
     pickup
    0.06
     Ein
    0.06
     Som
    0.06
     factors
    0.06
     Pall
    0.06
    Act Density 0.171%

    No Known Activations