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

    Neuronpedia

    INDEX
    Explanations

    wikipedia links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allery
    0.83
     televisions
    0.77
    TV
    0.76
    ong
    0.75
    skills
    0.74
     Tv
    0.73
    ԁ
    0.72
     tv
    0.71
     امریک
    0.70
     좋을
    0.69
    POSITIVE LOGITS
     resistor
    0.79
     trapping
    0.74
     identifik
    0.73
     callus
    0.71
     hunch
    0.71
     stress
    0.71
     გამ
    0.70
    ্যন্ত
    0.67
     permut
    0.67
    拄
    0.67
    Act Density 0.010%

    No Known Activations