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

    Neuronpedia

    INDEX
    Explanations

    references to the exterior of objects or structures

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

    exterior parts and construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     informée
    -0.72
     Trains
    -0.59
     Boltzmann
    -0.56
     Inscrivez
    -0.56
    Música
    -0.56
    Drinks
    -0.55
     pompe
    -0.54
    Walsh
    -0.54
    Bundes
    -0.53
     bershka
    -0.53
    POSITIVE LOGITS
     exterior
    1.78
     Exterior
    1.58
    Exterior
    1.55
    exterior
    1.53
     interior
    1.30
    interior
    1.16
    Interior
    1.13
     EXTER
    1.11
     Interior
    1.11
     exteriores
    1.10
    Act Density 0.004%

    No Known Activations