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

    Neuronpedia

    INDEX
    Explanations

    expressions of understanding or comprehension

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

    understanding concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RECOMM
    -0.39
     Wikimedijinoj
    -0.37
    AutoScaleMode
    -0.36
     kasarigan
    -0.35
     flip
    -0.34
     Picks
    -0.34
    kwds
    -0.34
    danh
    -0.34
     nakalista
    -0.33
    rungsseite
    -0.33
    POSITIVE LOGITS
     understanding
    1.69
     understand
    1.68
     Understanding
    1.56
    Understanding
    1.54
     understood
    1.51
    understand
    1.50
     Understand
    1.50
    Understand
    1.49
    understanding
    1.49
     understands
    1.48
    Act Density 0.085%

    No Known Activations