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

    Neuronpedia

    INDEX
    Explanations

    ancestry and inheritance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yr
    0.61
    ನಲ್ಲಿ
    0.55
    ers
    0.55
    yya
    0.55
     рост
    0.54
    ŠE
    0.53
     storico
    0.53
    //}
    0.52
    }$')
    0.52
    દ્ધ
    0.52
    POSITIVE LOGITS
    我也是
    0.62
     toma
    0.62
    তিপ
    0.62
    乍
    0.61
    FileOutputStream
    0.61
     tRNA
    0.61
    性
    0.59
     enhancer
    0.59
     Ці
    0.58
     consegue
    0.58
    Act Density 0.191%

    No Known Activations