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

    Neuronpedia

    INDEX
    Explanations

    parts of phrases or idioms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.39
     Dieses
    0.36
    wood
    0.35
     Dette
    0.35
    al
    0.34
    ab
    0.34
    matically
    0.34
     Mujhe
    0.34
    ied
    0.33
     समृ
    0.33
    POSITIVE LOGITS
     খ্যা
    0.37
    不如
    0.35
     για
    0.35
    というか
    0.34
     общения
    0.34
    اوى
    0.33
     όχι
    0.33
     dě
    0.32
    StudentNo
    0.32
     nhân
    0.31
    Act Density 0.311%

    No Known Activations