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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical proof and completion

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

    completing a proof or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laiko
    -0.37
     igång
    -0.36
     början
    -0.36
     ensuing
    -0.33
     fakty
    -0.31
     informaciones
    -0.31
     borderline
    -0.31
     ThemeData
    -0.30
     Übersetzung
    -0.28
     linguagem
    -0.28
    POSITIVE LOGITS
     completed
    0.99
     Completed
    0.98
     completing
    0.91
     Completing
    0.89
    Completed
    0.86
    completed
    0.86
     completes
    0.83
     completion
    0.81
     COMPLETED
    0.81
     Completion
    0.78
    Act Density 0.035%

    No Known Activations