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

    Neuronpedia

    INDEX
    Explanations

    reproducibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ively
    0.83
    u
    0.76
    ку
    0.74
    л
    0.74
    त
    0.72
    ки
    0.71
    х
    0.67
    ко
    0.65
    ان
    0.65
    𝚛
    0.65
    POSITIVE LOGITS
     nucleons
    0.74
     zichzelf
    0.71
    Iddict
    0.70
    equ
    0.68
    losti
    0.66
     löyty
    0.66
     salient
    0.64
     рассчиты
    0.63
    Accord
    0.62
    ωση
    0.62
    Act Density 0.004%

    No Known Activations