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

    Neuronpedia

    INDEX
    Explanations

    lyrics and songwriting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Popen
    0.84
    يد
    0.81
    𝗶
    0.80
    مكان
    0.78
    አ
    0.76
    রিতে
    0.75
    ل
    0.75
    න්
    0.74
    ላሉ
    0.74
    ेर
    0.73
    POSITIVE LOGITS
     ugl
    0.98
    )
    0.97
     broadcasts
    0.96
     sas
    0.93
     เว
    0.93
     emotes
    0.93
    iej
    0.93
     loafers
    0.92
    )+
    0.92
     huts
    0.91
    Act Density 0.006%

    No Known Activations