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

    Neuronpedia

    INDEX
    Explanations

    code and system operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Га
    0.70
    З
    0.70
    GPIO
    0.65
    Х
    0.63
    стройство
    0.62
    С
    0.62
     Ре
    0.62
     атом
    0.61
     Па
    0.61
     原子
    0.61
    POSITIVE LOGITS
     vast
    0.58
     exist
    0.55
     complex
    0.54
     all
    0.53
     compromises
    0.52
     more
    0.52
     existence
    0.52
     past
    0.51
     life
    0.51
     recent
    0.50
    Act Density 0.214%

    No Known Activations