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

    Neuronpedia

    INDEX
    Explanations

    references to error handling and exceptions in coding contexts

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

    Hebrew language markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     —
    -0.40
     pues
    -0.36
    Routledge
    -0.35
     producido
    -0.33
     tabletas
    -0.33
     dieux
    -0.32
    Array
    -0.32
      
    -0.32
    <eos>
    -0.32
     oignon
    -0.32
    POSITIVE LOGITS
     ל
    0.91
     לע
    0.88
     للمعارف
    0.86
     למ
    0.85
     לח
    0.84
     לפ
    0.83
     לת
    0.82
     לה
    0.80
     לג
    0.78
     לש
    0.77
    Act Density 0.000%

    No Known Activations