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

    Neuronpedia

    INDEX
    Explanations

    give you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BEEN
    0.90
    НИ
    0.88
     countless
    0.87
     અન્ય
    0.86
     dotyczą
    0.85
     autres
    0.85
     použív
    0.84
     been
    0.84
     praying
    0.84
    ‌هایی
    0.84
    POSITIVE LOGITS
     sake
    1.04
     Purposes
    0.97
     optimum
    0.97
     purposes
    0.96
    bear
    0.91
     했다
    0.91
     ול
    0.90
    peration
    0.89
     clarity
    0.88
    䡒
    0.87
    Act Density 0.709%

    No Known Activations