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

    Neuronpedia

    INDEX
    Explanations

    phrase or sentence structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alphanumeric
    0.50
     vassals
    0.49
    atively
    0.49
     dials
    0.48
     rodents
    0.47
     pre
    0.46
     analogies
    0.45
     pipes
    0.45
    ру
    0.44
     uffic
    0.44
    POSITIVE LOGITS
    TintColor
    0.48
    陸
    0.44
     अक्टूबर
    0.44
    鎵
    0.43
     его
    0.43
    اللي
    0.42
    核
    0.42
    ㄥ
    0.41
     લી
    0.41
    陆
    0.41
    Act Density 0.011%

    No Known Activations