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

    Neuronpedia

    INDEX
    Explanations

    period punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adore
    -0.06
    μένο
    -0.06
     analogue
    -0.06
     harmony
    -0.06
     Among
    -0.06
    _tax
    -0.06
     nửa
    -0.06
    Newsletter
    -0.06
    =mysql
    -0.05
    ышлен
    -0.05
    POSITIVE LOGITS
     گفت
    0.08
     disappoint
    0.07
    PlainOldData
    0.07
    	Task
    0.07
    џџџџџџџџ
    0.07
     Vu
    0.07
    /{
    0.07
     khác
    0.07
    _ur
    0.07
    _back
    0.07
    Act Density 0.066%

    No Known Activations