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

    Neuronpedia

    INDEX
    Explanations

    everything was perfect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いろんな
    0.42
     hinted
    0.39
     bored
    0.37
     metastatic
    0.36
     neurologic
    0.36
     hilar
    0.36
    分為
    0.35
    黾
    0.35
    ន្ទ
    0.35
     sensit
    0.34
    POSITIVE LOGITS
    perfect
    0.75
     Perfect
    0.73
    Perfect
    0.71
     perfect
    0.70
     функциони
    0.67
     perfecto
    0.65
     perfekt
    0.60
     perfecta
    0.60
     berfungsi
    0.60
     perfection
    0.59
    Act Density 0.002%

    No Known Activations