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

    Neuronpedia

    INDEX
    Explanations

    Listening, Relaxation, Rendering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensibilities
    0.50
     betrayal
    0.48
     windfall
    0.46
    テナンス
    0.45
     അപകട
    0.45
     pervasive
    0.45
     distanciation
    0.44
     parable
    0.44
     dynamism
    0.44
     abandonment
    0.44
    POSITIVE LOGITS
     connecté
    0.42
     पंप
    0.40
     connected
    0.39
    Filter
    0.38
     also
    0.37
     EMPTY
    0.37
     compiles
    0.37
     nemá
    0.37
     USING
    0.37
     succesfully
    0.37
    Act Density 0.009%

    No Known Activations