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

    Neuronpedia

    INDEX
    Explanations

    more robust, easier, cleaner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ይህ
    0.31
     Porque
    0.29
    觅
    0.27
    jeni
    0.27
    殄
    0.27
    PRNewswire
    0.27
    unread
    0.27
    ಂದರೆ
    0.27
    無し
    0.27
     हजारों
    0.26
    POSITIVE LOGITS
     coloquei
    0.44
     also
    0.42
     especially
    0.39
     약간
    0.39
     slightly
    0.38
    私も
    0.38
     também
    0.38
     också
    0.37
     también
    0.37
     मैंने
    0.37
    Act Density 0.079%

    No Known Activations