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

    Neuronpedia

    INDEX
    Explanations

    references to academic papers or formal research works

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

    introduction and paper

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.48
     للاسماء
    -0.44
    RTEE
    -0.44
    ंदीखरीदारी
    -0.42
     dignité
    -0.41
     stabilité
    -0.40
    SourceChecksum
    -0.40
    rungsseite
    -0.40
     sienta
    -0.39
     étanche
    -0.39
    POSITIVE LOGITS
    новништво
    0.52
    ActivityCompat
    0.51
     ModelExpression
    0.50
    ✨:
    0.50
    httphttps
    0.49
    #+#
    0.49
    MatButtonModule
    0.48
     kasarigan
    0.47
    orianCalendar
    0.46
    +#+
    0.46
    Act Density 0.052%

    No Known Activations