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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pattern
    0.58
     Guru
    0.57
    Infrastructure
    0.56
    തോ
    0.52
     Revista
    0.51
    Guru
    0.51
    セキュリティ
    0.51
    不高
    0.49
     Newspaper
    0.49
     ARISING
    0.49
    POSITIVE LOGITS
    న్ని
    0.66
     mè
    0.64
     resetting
    0.59
    ಮ್
    0.59
     battles
    0.57
    રમ
    0.57
     doux
    0.55
     rick
    0.55
     determinations
    0.55
     reset
    0.55
    Act Density 0.000%

    No Known Activations