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

    Neuronpedia

    INDEX
    Explanations

    customizing configuration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    meas
    0.35
    纲
    0.35
     நினைவுச்சின்ன
    0.35
     reich
    0.35
    ဲ့
    0.34
    逻
    0.34
     திருதியை
    0.33
    мин
    0.33
    革命
    0.33
     optimised
    0.33
    POSITIVE LOGITS
    ăl
    0.47
     servizi
    0.43
     locationManager
    0.43
     각종
    0.43
    ママ
    0.41
     Glance
    0.40
    Peng
    0.40
     रुचि
    0.40
     uri
    0.39
    而去
    0.38
    Act Density 0.002%

    No Known Activations