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

    Neuronpedia

    INDEX
    Explanations

    analyze and compare texts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BOARDSIZE
    0.47
    mesini
    0.44
     prenn
    0.43
     docile
    0.41
     Ace
    0.41
     generazione
    0.40
     पेटीएम
    0.39
     supaya
    0.39
     dijual
    0.39
     ناخذ
    0.38
    POSITIVE LOGITS
     centred
    0.41
    分鐘
    0.40
     focused
    0.39
     greeted
    0.38
     centering
    0.37
     clusters
    0.37
     inspecting
    0.37
    ·
    0.37
    接触
    0.37
     multi
    0.36
    Act Density 0.012%

    No Known Activations