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

    Neuronpedia

    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱼ
    0.46
    ktCap
    0.38
    私募基金
    0.35
    ].”
    0.33
    -​
    0.33
    船舶
    0.33
    ديث
    0.32
     probes
    0.32
    关节
    0.32
     Lumpur
    0.31
    POSITIVE LOGITS
    У
    0.66
    М
    0.64
    Б
    0.59
    Д
    0.59
    Ма
    0.57
    П
    0.56
    А
    0.55
    К
    0.55
    В
    0.53
    До
    0.52
    Act Density 0.183%

    No Known Activations