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

    Neuronpedia

    INDEX
    Explanations

    submit, failed, limitations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Stere
    0.43
     Maverick
    0.41
     आद
    0.38
     categorize
    0.38
     Stere
    0.38
     गोल
    0.38
     উপসং
    0.38
    Nicola
    0.37
     ask
    0.37
     muster
    0.37
    POSITIVE LOGITS
     Submitted
    0.50
     submitted
    0.46
     submitting
    0.46
     submit
    0.45
     제출
    0.44
     Submit
    0.42
     ব্যর্থ
    0.40
    submitted
    0.40
     failed
    0.39
    限制
    0.39
    Act Density 0.002%

    No Known Activations