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

    Neuronpedia

    INDEX
    Explanations

    circulatory system

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     by
    0.48
    历
    0.43
    หรับ
    0.42
    vez
    0.42
    жды
    0.42
    élé
    0.41
     with
    0.40
     mellem
    0.40
     for
    0.40
    是用
    0.40
    POSITIVE LOGITS
     धनु
    0.53
    рино
    0.52
    idcar
    0.52
    ープ
    0.52
    avirus
    0.51
     まで
    0.50
    та
    0.49
     antiguos
    0.49
     フェ
    0.48
    doubt
    0.48
    Act Density 0.004%

    No Known Activations