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

    Neuronpedia

    INDEX
    Explanations

    environment and damage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dern
    0.44
     नावा
    0.43
     biograf
    0.42
     tabi
    0.41
     Dimensions
    0.41
     р
    0.40
    संधान
    0.40
    一条
    0.40
     Finances
    0.40
    मेरा
    0.40
    POSITIVE LOGITS
     destruction
    0.44
     operatives
    0.43
    iserum
    0.43
    switchTo
    0.42
     observables
    0.39
    CBUUID
    0.39
    不一樣
    0.39
     regrowth
    0.39
     feedings
    0.39
     predomin
    0.39
    Act Density 0.001%

    No Known Activations