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

    Neuronpedia

    INDEX
    Explanations

    Account Registration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    те
    0.61
    но
    0.44
     с
    0.42
    тесь
    0.42
    цени
    0.41
     для
    0.41
    ке
    0.40
    決勝
    0.40
    кров
    0.39
     increasingly
    0.39
    POSITIVE LOGITS
     jednocześnie
    0.44
     innych
    0.43
    antz
    0.43
     puta
    0.43
     wybr
    0.43
     antennis
    0.42
    窅
    0.42
     naszych
    0.42
    莹
    0.42
     laga
    0.42
    Act Density 0.000%

    No Known Activations