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

    Neuronpedia

    INDEX
    Explanations

    references to archeological findings and human remains

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

    Remains, ruins, or fragments

    np_acts-logits-general · gemini-2.0-flash

    wreckage, ruins, and bones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mobileqq
    -0.68
     externi
    -0.58
     <=",
    -0.57
    ftagPool
    -0.54
    AddHtmlAttribute
    -0.53
    醐
    -0.53
    LiveData
    -0.51
    oa̍t
    -0.50
    LEncoder
    -0.49
    Télécharger
    -0.49
    POSITIVE LOGITS
     remnants
    1.08
     wreckage
    1.06
     debris
    1.02
     fragments
    0.99
     remains
    0.98
     strewn
    0.94
     discarded
    0.92
     ruins
    0.91
     débris
    0.86
     rubble
    0.85
    Act Density 0.348%

    No Known Activations