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

    Neuronpedia

    INDEX
    Explanations

    avenue names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wari
    0.42
     adipis
    0.41
    ല്ലാ
    0.40
     Mean
    0.40
     типи
    0.39
     VL
    0.38
     điển
    0.38
     inflammatory
    0.38
    典型
    0.38
     quibusdam
    0.38
    POSITIVE LOGITS
     Avenue
    2.27
     avenue
    2.20
     AVENUE
    2.05
     Ave
    1.88
     avenues
    1.84
     avenida
    1.77
    aven
    1.72
     ave
    1.65
    Ave
    1.63
     av
    1.62
    Act Density 0.016%

    No Known Activations