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

    Neuronpedia

    INDEX
    Explanations

    little

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t detect any patterns in the input.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     suspense
    -0.07
    upakan
    -0.07
     efekt
    -0.06
     shutter
    -0.06
     über
    -0.06
    termination
    -0.06
    .fa
    -0.06
    ощ
    -0.06
     daher
    -0.06
    staw
    -0.06
    POSITIVE LOGITS
     دام
    0.07
     дв
    0.07
    像是
    0.06
    ([&
    0.06
     America
    0.06
    iness
    0.06
     мом
    0.06
    มอ
    0.06
     Needed
    0.06
     DataBase
    0.06
    Act Density 0.009%

    No Known Activations