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

    Neuronpedia

    INDEX
    Explanations

    inquiry, questions or queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鲔
    0.65
    柽
    0.54
    齟
    0.53
    макра
    0.53
    镓
    0.52
     Alignment
    0.51
    鸬
    0.50
    缟
    0.50
    輥
    0.50
    螓
    0.50
    POSITIVE LOGITS
     netizens
    0.67
     domine
    0.63
     blushed
    0.62
     exquis
    0.60
     Xiao
    0.60
     despicable
    0.60
     Xia
    0.59
    了
    0.59
     unbearable
    0.59
     scolded
    0.58
    Act Density 0.146%

    No Known Activations