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

    Neuronpedia

    INDEX
    Explanations

    academic citation activity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Unterschiede
    0.47
    自觉
    0.46
    嚏
    0.43
    恻
    0.43
    车的
    0.43
    上传
    0.42
    ież
    0.41
    illions
    0.41
     Pencil
    0.40
    ście
    0.40
    POSITIVE LOGITS
    Cited
    0.50
     cit
    0.47
    From
    0.46
     tind
    0.45
     cited
    0.44
     derive
    0.43
     referencia
    0.42
    Impact
    0.42
     citrate
    0.41
    引用
    0.41
    Act Density 0.003%

    No Known Activations