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

    Neuronpedia

    INDEX
    Explanations

    cotton pad or swab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    شتی
    0.56
    لی
    0.52
     produksi
    0.50
    ك
    0.49
    غ
    0.49
     don
    0.49
    λλ
    0.49
    v
    0.48
     equatorial
    0.48
    k
    0.47
    POSITIVE LOGITS
    ↵
    0.68
    is
    0.61
     Debe
    0.59
    ፎ
    0.59
    lere
    0.58
     VH
    0.57
     Chirurg
    0.57
     Ар
    0.56
     OFW
    0.56
    đe
    0.56
    Act Density 0.001%

    No Known Activations