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

    Neuronpedia

    INDEX
    Explanations

    assignments and object initializations in code

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

    object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thâu
    -0.66
     الرياضيه
    -0.56
    Autoritní
    -0.55
     ویکی‌پدی
    -0.54
     ujednoznacz
    -0.54
    DockStyle
    -0.53
     kasarigan
    -0.53
     stanovnika
    -0.52
    Życiorys
    -0.52
    ImageContext
    -0.50
    POSITIVE LOGITS
     twice
    0.35
     ration
    0.34
     chemical
    0.34
     hemd
    0.34
    ustimmung
    0.33
    URLException
    0.33
     three
    0.33
    AnimationsModule
    0.32
     initial
    0.32
     forward
    0.32
    Act Density 0.010%

    No Known Activations