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

    Neuronpedia

    INDEX
    Explanations

    specific concepts and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hashing
    0.48
     reflux
    0.47
     troubles
    0.46
    чением
    0.45
    บวน
    0.45
     ფუნქ
    0.43
     lookup
    0.43
    ၚ
    0.43
     refrain
    0.43
     chaperone
    0.43
    POSITIVE LOGITS
     αυτο
    0.46
    小
    0.44
    adas
    0.42
     మ
    0.42
    ai
    0.41
     feitos
    0.41
     Aquarius
    0.41
     Ива
    0.41
    TextInput
    0.40
    场
    0.40
    Act Density 0.003%

    No Known Activations