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

    Neuronpedia

    INDEX
    Explanations

    assessments and discussions of information transfer processes

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

    Sentences ending with periods

    np_acts-logits-general · gemini-2.0-flash

    introducing arguments and research

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     You
    -0.72
    You
    -0.67
    you
    -0.67
     somebody
    -0.64
     you
    -0.64
     Somebody
    -0.63
     اگه
    -0.61
    Somebody
    -0.61
     Someone
    -0.60
     Have
    -0.59
    POSITIVE LOGITS
     Drawing
    0.90
    Accordingly
    0.89
     Importantly
    0.89
     Accordingly
    0.88
     drawing
    0.85
     Whereas
    0.84
    Drawing
    0.84
    Whereas
    0.82
     while
    0.80
    Focusing
    0.80
    Act Density 0.625%

    No Known Activations