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

    Neuronpedia

    INDEX
    Explanations

    also / moreover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    У
    0.64
    И
    0.64
    Э
    0.50
    С
    0.46
    Ч
    0.44
    코
    0.43
    Как
    0.43
    用
    0.43
    Я
    0.42
    А
    0.42
    POSITIVE LOGITS
     inoltre
    0.79
     Also
    0.59
     Inoltre
    0.59
     também
    0.58
     también
    0.55
     hingegen
    0.54
     također
    0.53
    anwhile
    0.52
     also
    0.52
     також
    0.52
    Act Density 0.027%

    No Known Activations