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

    Neuronpedia

    INDEX
    Explanations

    references to car models and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    properties, houses, for sale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    component
    -0.31
     experiment
    -0.31
     HARRIS
    -0.31
     Harris
    -0.29
     gere
    -0.29
     Singh
    -0.28
     الحره
    -0.28
     Raya
    -0.28
    ensaft
    -0.27
    Component
    -0.27
    POSITIVE LOGITS
    uxxxx
    0.76
    AddTagHelper
    0.68
    EDEFAULT
    0.67
    DockStyle
    0.66
    InjectAttribute
    0.65
    featureID
    0.65
     Houſe
    0.64
    SharedDtor
    0.61
     intStringLen
    0.61
    inWeight
    0.61
    Act Density 0.068%

    No Known Activations