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

    Neuronpedia

    INDEX
    Explanations

    AI product development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    为例
    0.47
    頊
    0.46
    Deux
    0.45
    <unused338>
    0.45
    riter
    0.44
    Statements
    0.44
    퍼
    0.44
     書い
    0.43
    GoalState
    0.43
    COc
    0.43
    POSITIVE LOGITS
     e
    0.45
     get
    0.38
    0.38
     Nothing
    0.37
     gotten
    0.36
     Be
    0.36
     players
    0.35
     Tom
    0.35
     SAD
    0.35
    opens
    0.35
    Act Density 0.000%

    No Known Activations