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

    Neuronpedia

    INDEX
    Explanations

    left direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    URNING
    0.40
    নং
    0.40
    তুম
    0.39
    ্লিষ্ট
    0.38
    ugno
    0.38
     साधन
    0.37
    ंक्शन
    0.37
    ਹੀਂ
    0.37
     Archivado
    0.37
    __:
    0.37
    POSITIVE LOGITS
     fact
    0.45
     left
    0.44
    fact
    0.43
     Antib
    0.41
     Fact
    0.40
     esquerda
    0.39
     Left
    0.38
     Waterloo
    0.38
    左
    0.37
    Touch
    0.37
    Act Density 0.000%

    No Known Activations