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

    Neuronpedia

    INDEX
    Explanations

    focus on things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ore
    0.48
    ie
    0.45
    ard
    0.45
    га
    0.45
    ake
    0.44
    arlane
    0.44
    ian
    0.43
    ეც
    0.43
    enje
    0.43
    obie
    0.43
    POSITIVE LOGITS
     dispers
    0.50
     patented
    0.44
     分
    0.42
     wastewater
    0.41
     torpedo
    0.41
     Timurtaş
    0.40
     Utilis
    0.39
     bearings
    0.39
     Propri
    0.39
     RxSwift
    0.39
    Act Density 0.017%

    No Known Activations