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

    Neuronpedia

    INDEX
    Explanations

    expressing past intentions or thoughts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    سی
    0.74
     yaptı
    0.70
     নয়া
    0.65
     राहणार
    0.63
     atualmente
    0.63
     batalha
    0.62
     রাশিয়া
    0.61
    ູນ
    0.61
     baru
    0.60
     धातु
    0.60
    POSITIVE LOGITS
    ي
    0.95
    The
    0.83
     The
    0.77
    et
    0.77
    по
    0.75
    i
    0.71
     ursprünglich
    0.69
    ed
    0.68
                    
    0.67
    brief
    0.67
    Act Density 0.142%

    No Known Activations