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

    Neuronpedia

    INDEX
    Explanations

    LoRA, Lopburi, Loch Ness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Past
    0.77
     habituellement
    0.76
    ம்
    0.76
     terrestrial
    0.76
     past
    0.75
    ტურ
    0.75
     innoc
    0.75
    दम
    0.74
     dama
    0.72
     nered
    0.72
    POSITIVE LOGITS
     lắng
    1.10
     कट
    0.98
    yal
    0.92
     affiliate
    0.86
     লিখিত
    0.85
    ̀i
    0.85
    formatter
    0.84
    頫
    0.84
    ഡ്
    0.82
    oney
    0.82
    Act Density 0.148%

    No Known Activations