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

    Neuronpedia

    INDEX
    Explanations

    time indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     undertaken
    0.39
     предпринима
    0.37
     establecidas
    0.36
     entailed
    0.35
     establecidos
    0.34
     рассматри
    0.33
     estabelecer
    0.33
     diminishes
    0.32
     происходит
    0.32
     способствует
    0.32
    POSITIVE LOGITS
    ্ধ
    0.32
    Pixel
    0.31
    Trial
    0.31
    miyor
    0.31
    は
    0.31
     Monsters
    0.30
    adan
    0.29
    ັງ
    0.29
    achte
    0.29
    țit
    0.29
    Act Density 0.000%

    No Known Activations