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

    Neuronpedia

    INDEX
    Explanations

    "that"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ду
    0.87
    itattu
    0.80
     राधे
    0.78
    gnu
    0.77
    TGF
    0.76
     São
    0.76
    ுங்கள்
    0.75
     том
    0.74
    MyHomePage
    0.74
    stoke
    0.74
    POSITIVE LOGITS
     exposes
    0.89
     illuminates
    0.86
     momento
    0.83
     smells
    0.82
     einige
    0.78
     involves
    0.78
     necessitates
    0.78
    또한
    0.77
     सारे
    0.77
     mismas
    0.76
    Act Density 0.000%

    No Known Activations