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

    Neuronpedia

    INDEX
    Explanations

    expressions of understanding or appreciation for different perspectives

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

    comprehension and realization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsxFileName
    -0.54
    Ƚ
    -0.54
     imprimée
    -0.54
    antaranya
    -0.53
     Winaray
    -0.53
    transQ
    -0.52
    msgTypes
    -0.52
     odeur
    -0.50
     argint
    -0.50
     незавершена
    -0.50
    POSITIVE LOGITS
     understandable
    0.48
    speed
    0.44
     reasons
    0.43
     speed
    0.42
     why
    0.41
     EZ
    0.41
     Cav
    0.40
     hel
    0.40
     cav
    0.40
    hésitez
    0.40
    Act Density 0.023%

    No Known Activations