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

    Neuronpedia

    INDEX
    Explanations

    no access or limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patterned
    0.40
     vertebrate
    0.37
     biod
    0.36
     ricon
    0.36
    sklär
    0.36
     Tatha
    0.35
    altro
    0.35
     Eber
    0.35
     chromatography
    0.34
    christ
    0.34
    POSITIVE LOGITS
     việc
    0.56
     không
    0.48
    Não
    0.46
    บาง
    0.43
    不仅仅
    0.42
     требо
    0.42
    否则
    0.42
     невозможно
    0.42
    しない
    0.41
    Không
    0.41
    Act Density 0.004%

    No Known Activations