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

    Neuronpedia

    INDEX
    Explanations

    randomness and temperature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    槭
    0.40
     simplicity
    0.39
     enthusiasm
    0.38
     ~/
    0.38
     easily
    0.37
     essentially
    0.37
    的一部分
    0.36
    叡
    0.36
     Screen
    0.35
    ENABLE
    0.35
    POSITIVE LOGITS
    잣
    0.43
     మరి
    0.43
    cknowledg
    0.40
     činjen
    0.39
    agé
    0.39
     peças
    0.38
     रखिए
    0.38
    ：
    0.37
    郦
    0.37
     einzelnen
    0.37
    Act Density 0.001%

    No Known Activations