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

    Neuronpedia

    INDEX
    Explanations

    sequence positions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WeakTable
    0.41
    她们
    0.40
     তাদেরকে
    0.40
     seraient
    0.40
     देतात
    0.37
     исключительно
    0.37
     عليها
    0.36
    illin
    0.36
     इन्हें
    0.36
     tendría
    0.36
    POSITIVE LOGITS
    second
    0.51
    SECOND
    0.46
     second
    0.44
    thirds
    0.42
    THIRD
    0.41
    第二
    0.40
    Q
    0.40
    ‘’
    0.39
     SECOND
    0.39
    第三
    0.38
    Act Density 0.000%

    No Known Activations