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

    Neuronpedia

    INDEX
    Explanations

    multilingual snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unch
    0.40
     সবাইকে
    0.39
    程
    0.38
     Un
    0.38
     kes
    0.38
    iec
    0.37
     Burning
    0.37
     Belief
    0.36
    we
    0.36
    ましたが
    0.36
    POSITIVE LOGITS
     factorizar
    0.42
     tuxedo
    0.39
    蕨
    0.39
    adoo
    0.38
    তুন
    0.37
    ərb
    0.37
     武田
    0.37
     تصير
    0.37
    ânt
    0.36
     гиб
    0.36
    Act Density 0.001%

    No Known Activations