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

    Neuronpedia

    INDEX
    Explanations

    more adept, limited

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    spunkt
    0.55
     réparation
    0.50
     ремонта
    0.50
    kult
    0.49
    minim
    0.49
    rás
    0.49
    passion
    0.47
    punkt
    0.46
    marg
    0.46
    picks
    0.45
    POSITIVE LOGITS
    веро
    0.47
     underground
    0.45
     moneys
    0.45
     buyer
    0.44
    साठी
    0.44
    ಾರ್
    0.44
     Mexican
    0.43
     Shaped
    0.42
     mx
    0.42
    িত
    0.42
    Act Density 0.001%

    No Known Activations