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

    Neuronpedia

    INDEX
    Explanations

    keyword planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     onshore
    0.79
     चार्ट
    0.73
    籌
    0.71
    ቃዎች
    0.70
     Sought
    0.68
    ውነ
    0.68
    লীগের
    0.67
     ہوگ
    0.66
    重庆
    0.64
     Baton
    0.63
    POSITIVE LOGITS
     conjure
    0.78
     love
    0.75
    manship
    0.73
     любовь
    0.72
     putting
    0.71
     lighting
    0.70
     JOURNAL
    0.70
     puts
    0.69
     put
    0.69
    landers
    0.69
    Act Density 0.004%

    No Known Activations