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

    Neuronpedia

    INDEX
    Explanations

    print() function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鬯
    0.88
    ductor
    0.87
    andte
    0.78
     combinação
    0.75
     combina
    0.74
    끗
    0.74
     ৬৮
    0.73
     ক্ষমতাসীন
    0.72
     সরাসরি
    0.72
    собенно
    0.72
    POSITIVE LOGITS
     Nevertheless
    1.50
     Nonetheless
    1.47
    Nonetheless
    1.37
    Nevertheless
    1.36
     Lots
    1.30
     Should
    1.22
    Lots
    1.19
     Numerous
    1.18
     Individuals
    1.17
     Cont
    1.16
    Act Density 0.020%

    No Known Activations