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

    Neuronpedia

    INDEX
    Explanations

    references to definitions and the act of defining concepts

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

    followed by definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]=>
    -0.53
    AxisAlignment
    -0.42
    Hochspringen
    -0.40
    хьтан
    -0.40
     piper
    -0.36
     cherchés
    -0.36
    Bukkit
    -0.36
    </tfoot>
    -0.35
    Lähteet
    -0.35
     pytest
    -0.35
    POSITIVE LOGITS
     definition
    0.90
     définition
    0.84
     definición
    0.82
     definição
    0.80
     definitions
    0.79
    definition
    0.77
     Definition
    0.76
     DEFINITION
    0.76
    DEFINITION
    0.74
    Pengertian
    0.68
    Act Density 0.486%

    No Known Activations