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

    Neuronpedia

    INDEX
    Explanations

    positive affirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     خلاف
    0.43
     infallible
    0.40
    ोब
    0.39
     بلکه
    0.39
    AgentError
    0.38
     groupBox
    0.37
    냐면
    0.37
    のだが
    0.36
     trội
    0.35
    িকাংশ
    0.35
    POSITIVE LOGITS
     Congratulations
    1.20
     congrats
    1.13
     congratulations
    1.11
     Congrats
    1.09
    Congratulations
    1.02
    Congrats
    0.98
     Sounds
    0.88
     glad
    0.88
     Glad
    0.87
     congratulated
    0.86
    Act Density 0.032%

    No Known Activations