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

    Neuronpedia

    INDEX
    Explanations

    program arguments and accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glaring
    0.53
     breakfasts
    0.50
     magg
    0.49
    те
    0.47
     tels
    0.47
    をも
    0.47
     ट्रॉ
    0.47
    வற்றை
    0.46
     theses
    0.46
    ור
    0.46
    POSITIVE LOGITS
    Iranian
    0.54
    splitter
    0.50
    运营商
    0.47
    Division
    0.47
    irman
    0.45
    idens
    0.44
    परेशन
    0.44
    old
    0.44
    reachable
    0.44
    全新
    0.43
    Act Density 0.001%

    No Known Activations