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

    Neuronpedia

    INDEX
    Explanations

    punctuation in quotes/dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ingredients
    -0.07
    	SP
    -0.06
    reat
    -0.06
    losure
    -0.06
    мів
    -0.06
    .HCM
    -0.06
    ्रस
    -0.06
    nuts
    -0.06
    _sentences
    -0.06
     Анг
    -0.06
    POSITIVE LOGITS
     effic
    0.07
    middle
    0.07
     anxious
    0.07
    nahme
    0.07
     fortunes
    0.06
     معل
    0.06
     gave
    0.06
     surviving
    0.06
     الأولى
    0.06
    -export
    0.06
    Act Density 0.020%

    No Known Activations