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

    Neuronpedia

    INDEX
    Explanations

    comparing two items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    られて
    0.39
     Trebuie
    0.38
     नसते
    0.38
     آہستہ
    0.37
     Cabe
    0.37
     Rider
    0.36
     devem
    0.36
     sustancia
    0.35
     lingk
    0.35
     म्हटले
    0.35
    POSITIVE LOGITS
    ovatel
    0.43
    ---|
    0.42
    鈕
    0.41
    )--
    0.39
    نون
    0.39
     सैफ
    0.39
    Ᏻ
    0.38
    兗
    0.38
     kites
    0.38
    ADY
    0.37
    Act Density 0.008%

    No Known Activations