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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Grid
    -0.07
     하는
    -0.07
     owes
    -0.07
    (so
    -0.06
     En
    -0.06
     weir
    -0.06
     YES
    -0.06
    ());
↵
    -0.06
    itarian
    -0.06
     سیم
    -0.06
    POSITIVE LOGITS
     pimp
    0.07
     эп
    0.06
    licate
    0.06
    jp
    0.06
     Predictor
    0.06
     naval
    0.06
    acob
    0.06
    ท
    0.06
    ธาน
    0.06
    ACP
    0.06
    Act Density 0.043%

    No Known Activations