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

    Neuronpedia

    INDEX
    Explanations

    errors loading or fetching resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     முடிந்த
    0.40
    を除く
    0.40
     کل
    0.40
     ज्व
    0.39
     వెళ్లి
    0.39
     書い
    0.39
    汔
    0.39
     विधि
    0.39
     Conclusion
    0.38
    ếng
    0.37
    POSITIVE LOGITS
     feit
    0.45
     this
    0.44
     contenu
    0.40
    giphy
    0.39
    文化的
    0.38
    ignan
    0.37
    load
    0.37
     Northwestern
    0.37
    this
    0.37
     your
    0.36
    Act Density 0.001%

    No Known Activations