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

    Neuronpedia

    INDEX
    Explanations

    accessing members or checking existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     r
    0.85
     t
    0.82
     b
    0.80
     p
    0.77
    T
    0.76
     T
    0.74
     y
    0.73
    大
    0.70
    OS
    0.70
    L
    0.70
    POSITIVE LOGITS
    质疑
    0.82
     გამოყენ
    0.80
     Timurtaş
    0.79
     информацию
    0.77
    嬗
    0.77
     нәрсә
    0.75
    калә
    0.75
     شرطونو
    0.73
    avasena
    0.73
     шабло
    0.73
    Act Density 0.706%

    No Known Activations