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

    Neuronpedia

    INDEX
    Explanations

    body parts, conditions, and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     этого
    0.49
    거든요
    0.48
     faptul
    0.47
    сал
    0.47
     tedes
    0.46
    ています
    0.46
    нная
    0.45
    薬品
    0.45
     openness
    0.45
     arches
    0.45
    POSITIVE LOGITS
     이미지
    0.47
    ana
    0.45
     血
    0.44
     المخ
    0.43
     피부
    0.42
     독
    0.42
    anch
    0.42
     肌
    0.41
     வே
    0.40
    anç
    0.40
    Act Density 0.001%

    No Known Activations