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

    Neuronpedia

    INDEX
    Explanations

    simplify things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nvidia
    0.83
     preocup
    0.82
     बीजेपी
    0.81
     convenient
    0.79
    olutely
    0.79
     Friendly
    0.78
    ᱠ
    0.78
     andDevice
    0.78
    льності
    0.77
     adverb
    0.76
    POSITIVE LOGITS
    0.83
    Downloaded
    0.80
    0.80
    Page
    0.78
    0.76
    www
    0.75
    0.75
    0.73
    0.72
    indd
    0.72
    Act Density 0.003%

    No Known Activations