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

    Neuronpedia

    INDEX
    Explanations

    conditioned positive outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     často
    0.50
     했다
    0.46
     često
    0.46
     தொடங்கிய
    0.45
     często
    0.44
     Tried
    0.44
    prüng
    0.44
    Tried
    0.43
    forEach
    0.43
     এসেছেন
    0.43
    POSITIVE LOGITS
     successfully
    0.86
     successful
    0.77
     succeeds
    0.76
     berhasil
    0.72
     réussir
    0.71
    成功
    0.69
     succesfully
    0.69
     breakthroughs
    0.67
     суме
    0.67
    Successfully
    0.66
    Act Density 0.017%

    No Known Activations