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

    Neuronpedia

    INDEX
    Explanations

    Philosophers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Destroy
    -0.06
     traces
    -0.06
    losti
    -0.06
    .peek
    -0.06
    slots
    -0.06
    Packet
    -0.06
     более
    -0.06
     AFP
    -0.06
    cido
    -0.06
    >.</
    -0.06
    POSITIVE LOGITS
    =item
    0.07
     зобов
    0.07
    表
    0.07
    scheduled
    0.06
     внутри
    0.06
     نظ
    0.06
     summary
    0.06
    udiante
    0.06
     annotations
    0.06
    	pl
    0.06
    Act Density 0.013%

    No Known Activations