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

    Neuronpedia

    INDEX
    Explanations

    relating to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ील
    0.49
     رفض
    0.47
     pounding
    0.43
    拒绝
    0.41
    法施行令
    0.41
    蔦
    0.41
    ೀಯ
    0.40
    居住
    0.39
    કલ
    0.39
    構
    0.39
    POSITIVE LOGITS
    duh
    0.45
    ips
    0.44
    dates
    0.42
    mea
    0.41
    cer
    0.41
     '')
    0.41
    W
    0.41
    ro
    0.40
    ckers
    0.40
     بگ
    0.40
    Act Density 24.633%

    No Known Activations