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

    Neuronpedia

    INDEX
    Explanations

    high values or instances in data representing elevation or intensity

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

    high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laſſen
    -0.63
    opsis
    -0.63
     müſſen
    -0.60
     AssemblyProduct
    -0.60
    tent
    -0.59
    erjee
    -0.59
    ecraft
    -0.58
    embe
    -0.57
    mella
    -0.57
    amante
    -0.56
    POSITIVE LOGITS
     high
    1.79
     High
    1.66
    High
    1.63
    high
    1.61
     HIGH
    1.38
    HIGH
    1.32
    高
    1.16
     yüksek
    1.05
     vysok
    1.02
     高
    1.00
    Act Density 0.071%

    No Known Activations