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

    Neuronpedia

    INDEX
    Explanations

    forums and chat discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ज्ञ
    0.46
    йної
    0.46
    ৪
    0.42
    Actress
    0.42
    Electrical
    0.41
    Meas
    0.40
    Director
    0.40
    Answer
    0.39
    ARY
    0.39
    ร
    0.39
    POSITIVE LOGITS
     අ
    0.50
     Ibrahim
    0.48
     скла
    0.46
     combinatorial
    0.46
     Man
    0.46
     modified
    0.46
     Cordova
    0.45
     Craigslist
    0.45
     Kuwait
    0.44
     screwing
    0.44
    Act Density 0.000%

    No Known Activations