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

    Neuronpedia

    INDEX
    Explanations

    security, orm, webdriver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     गर्भावस्था
    0.38
     بالغ
    0.38
     कोतवाली
    0.38
     கண்காணி
    0.37
     समाधान
    0.36
     schließen
    0.36
     kontek
    0.36
     成
    0.36
    نى
    0.36
    Premi
    0.35
    POSITIVE LOGITS
     zeolite
    0.40
    ફ
    0.39
     proc
    0.38
     pepper
    0.38
    oselect
    0.37
    酸
    0.37
     acid
    0.37
    खुद
    0.36
    eterm
    0.36
     Acid
    0.35
    Act Density 0.001%

    No Known Activations