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

    Neuronpedia

    INDEX
    Explanations

    languages and multilingual indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Preferably
    0.41
    并在
    0.41
    並且
    0.39
    力和
    0.37
    包括
    0.37
     包括
    0.37
     включая
    0.36
    并将
    0.36
    并且
    0.33
     Jeżeli
    0.33
    POSITIVE LOGITS
     erstmals
    0.37
    क्स
    0.37
     등을
    0.36
     etc
    0.36
     etcétera
    0.36
     со
    0.34
     maupun
    0.34
    ştik
    0.34
     وغيرها
    0.34
     usw
    0.33
    Act Density 0.029%

    No Known Activations