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

    Neuronpedia

    INDEX
    Explanations

    foreign names and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BRO
    0.49
    Colour
    0.47
     items
    0.47
    T
    0.46
    COUNTRY
    0.45
    bro
    0.45
    utility
    0.45
     protective
    0.45
    standalone
    0.44
    Protect
    0.44
    POSITIVE LOGITS
     theologian
    0.50
    笃
    0.47
     Jérôme
    0.46
     Саша
    0.44
     algéb
    0.42
     Dieu
    0.41
    ämä
    0.41
     secteur
    0.41
    ৫৫
    0.40
     déterminer
    0.40
    Act Density 0.008%

    No Known Activations