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

    Neuronpedia

    INDEX
    Explanations

    ise

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the Devise authentication library (the token “Devise”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .exp
    -0.06
     ENERGY
    -0.06
     mạch
    -0.06
     babe
    -0.06
     //</
    -0.06
    .ValidationError
    -0.06
    ^\
    -0.06
    .sell
    -0.06
    /company
    -0.06
     кур
    -0.06
    POSITIVE LOGITS
    actical
    0.07
    uitar
    0.07
     SDS
    0.06
     Quar
    0.06
    IGIN
    0.06
     chimpan
    0.06
    ivil
    0.06
    outines
    0.06
    ouse
    0.06
     realloc
    0.06
    Act Density 0.002%

    No Known Activations