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

    Neuronpedia

    INDEX
    Explanations

    time and periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﮅ
    0.37
     flakes
    0.36
     sulfides
    0.35
    idable
    0.35
    chende
    0.34
     Tories
    0.34
    7
    0.33
     shards
    0.33
    ൺലൈ
    0.33
    ant
    0.33
    POSITIVE LOGITS
     Clín
    0.42
    الأ
    0.41
    🕣
    0.40
     જ્યાં
    0.39
    🕖
    0.39
     після
    0.39
     Starring
    0.39
    ☕
    0.39
     சுற்றுலா
    0.38
     mân
    0.38
    Act Density 0.003%

    No Known Activations