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

    Neuronpedia

    INDEX
    Explanations

    references to workshops

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

    workshop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /*
    -0.58
    reportWebVitals
    -0.55
    TemporalType
    -0.48
    RenderAtEndOf
    -0.46
     Numerade
    -0.46
    lgari
    -0.45
     المعيارى
    -0.45
    Vanjske
    -0.45
    PendingIntent
    -0.45
     canst
    -0.45
    POSITIVE LOGITS
     workshop
    2.08
     Workshop
    2.05
    Workshop
    1.88
    workshop
    1.84
     WORKSHOP
    1.72
     workshops
    1.17
     Workshops
    1.15
     Werkstatt
    0.96
    Workshops
    0.93
     atelier
    0.92
    Act Density 0.002%

    No Known Activations