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

    Neuronpedia

    INDEX
    Explanations

    prepositions and their usage in various contexts

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

    people on horseback or performing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.55
     Infórmanos
    -0.54
    Tembelea
    -0.52
    깥
    -0.48
     amitié
    -0.47
     Autorizaciones
    -0.46
     camadas
    -0.45
     desmotivaciones
    -0.44
     sementes
    -0.43
    umumkan
    -0.43
    POSITIVE LOGITS
     standing
    0.44
     acting
    0.44
     Dealing
    0.42
     sitting
    0.42
     dressed
    0.42
     performing
    0.41
     lined
    0.41
     portraying
    0.41
     running
    0.40
     dealing
    0.40
    Act Density 0.037%

    No Known Activations