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

    Neuronpedia

    INDEX
    Explanations

    first mention or appearance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     odgovor
    0.46
    ကြီး
    0.40
    isDirectory
    0.39
     duniya
    0.39
     Interpretation
    0.38
    vigor
    0.38
     interpretation
    0.38
    समझ
    0.37
    azem
    0.36
    صميم
    0.36
    POSITIVE LOGITS
     mentions
    1.25
     mention
    1.17
     упомина
    1.17
     언급
    1.04
     mentioning
    1.01
     occurrences
    0.99
    提及
    0.98
     Mention
    0.98
     repeated
    0.98
    出现的
    0.97
    Act Density 0.059%

    No Known Activations