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

    Neuronpedia

    INDEX
    Explanations

    languages after "in"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JDK
    0.48
     CUT
    0.45
    CRUD
    0.45
     IDE
    0.44
     PEC
    0.44
     Taro
    0.44
     SIM
    0.44
     Tort
    0.42
     CRUD
    0.42
    /
    0.42
    POSITIVE LOGITS
    efeuille
    0.49
    fohlen
    0.48
     anglès
    0.47
    🎱
    0.46
    ظم
    0.44
    ইংরেজি
    0.44
    英文
    0.44
    ार्थ
    0.44
    ouden
    0.43
     इंग्लिश
    0.43
    Act Density 0.007%

    No Known Activations