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

    Neuronpedia

    INDEX
    Explanations

    people or roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     userRoutes
    0.79
     decis
    0.79
     culminating
    0.76
     fanatics
    0.74
     monsters
    0.74
     wigs
    0.73
     elongate
    0.72
    ര്‍ച്ച
    0.72
    어를
    0.72
     নিজেদের
    0.72
    POSITIVE LOGITS
     ஒருவர்
    1.11
    গিত
    0.95
    hood
    0.95
    шал
    0.92
    дает
    0.87
     пытается
    0.85
    lerden
    0.85
    وں
    0.85
    izuje
    0.84
    ischen
    0.83
    Act Density 0.010%

    No Known Activations