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

    Neuronpedia

    INDEX
    Explanations

    ta-da or google search

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Soap
    0.41
    alama
    0.39
    పతి
    0.39
     Soap
    0.38
    ufa
    0.38
    Wra
    0.37
    CFT
    0.37
     soaps
    0.36
    soap
    0.36
    عبد
    0.36
    POSITIVE LOGITS
     główn
    0.42
     hlavní
    0.41
    ГУ
    0.40
     vezes
    0.40
    atu
    0.40
     Глав
    0.39
    Hlav
    0.39
     глав
    0.39
     lily
    0.38
     hlav
    0.38
    Act Density 0.001%

    No Known Activations