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

    Neuronpedia

    INDEX
    Explanations

    tone and style adjustment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     הז
    0.40
     Polyester
    0.40
     बॉल
    0.39
     Capacitor
    0.38
     बघेल
    0.38
     करवाए
    0.38
     Bagley
    0.38
     गेंद
    0.37
     televiz
    0.37
     نما
    0.37
    POSITIVE LOGITS
     steeper
    0.42
     carnage
    0.41
    鉴
    0.41
    ISTR
    0.41
     greater
    0.41
    greater
    0.41
     harder
    0.41
     raising
    0.40
     Fra
    0.39
     homogeneous
    0.39
    Act Density 0.005%

    No Known Activations