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

    Neuronpedia

    INDEX
    Explanations

    code syntax and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hj
    0.45
     Answer
    0.43
    answer
    0.41
    enco
    0.41
    Interview
    0.41
     Interview
    0.41
    Yesterday
    0.41
     More
    0.40
    ки
    0.39
    undefined
    0.39
    POSITIVE LOGITS
    匐
    0.50
     colores
    0.44
    ᱔
    0.42
     الغذ
    0.42
     substitutional
    0.42
     charges
    0.41
     couleurs
    0.40
    縄
    0.39
    唳
    0.39
     rulings
    0.39
    Act Density 0.000%

    No Known Activations