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

    Neuronpedia

    INDEX
    Explanations

    separately listed items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आणि
    0.45
     ਅਤੇ
    0.42
     અને
    0.40
    ແລະ
    0.40
     ಮತ್ತು
    0.38
     and
    0.37
    性和
    0.37
    力和
    0.36
     và
    0.36
     និង
    0.34
    POSITIVE LOGITS
     각각
    0.43
    分别
    0.41
     respectively
    0.38
     alike
    0.38
     respectivamente
    0.38
    それぞれ
    0.35
     respectiv
    0.35
    分别是
    0.33
    各有
    0.32
    といった
    0.32
    Act Density 0.618%

    No Known Activations