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

    Neuronpedia

    INDEX
    Explanations

    Indo-Pacific

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    τίας
    0.53
    MAR
    0.52
    МА
    0.52
    БУ
    0.52
    uah
    0.50
    bewer
    0.50
     जिसने
    0.48
     जिन्होंने
    0.48
    ప్ర
    0.47
    想到
    0.46
    POSITIVE LOGITS
     服务
    0.49
     berikut
    0.48
    leted
    0.45
     کہ
    0.44
    )
    0.44
     環
    0.43
     갈
    0.43
    రం
    0.43
    rofoam
    0.42
     Niro
    0.42
    Act Density 0.001%

    No Known Activations