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

    Neuronpedia

    INDEX
    Explanations

    avoiding unwanted artifacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ião
    0.50
    적
    0.44
    王
    0.44
    superuser
    0.44
     cryptographic
    0.43
    اعری
    0.43
    веря
    0.43
    젹
    0.42
    بر
    0.42
     candid
    0.41
    POSITIVE LOGITS
     Jawa
    0.52
    hips
    0.52
     Ayam
    0.52
     malo
    0.50
     Guns
    0.48
     Gund
    0.47
     Tata
    0.47
     Mardi
    0.47
    im
    0.46
     આવ
    0.46
    Act Density 0.004%

    No Known Activations