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

    Neuronpedia

    INDEX
    Explanations

    potential outcomes and risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     supposedly
    0.48
     allegedly
    0.48
     reportedly
    0.47
     Basics
    0.47
    gger
    0.46
     apparently
    0.44
    工夫
    0.43
     arguably
    0.43
    inalg
    0.43
     Apparently
    0.43
    POSITIVE LOGITS
     outcomes
    0.81
     outcome
    0.78
     future
    0.70
     pitfalls
    0.67
    outcome
    0.63
     Outcomes
    0.61
     toekom
    0.61
    future
    0.59
     scenario
    0.57
     scenarios
    0.57
    Act Density 0.493%

    No Known Activations