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

    Neuronpedia

    INDEX
    Explanations

    benefit amount increases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     intuition
    0.89
     personalisation
    0.85
     MNIST
    0.83
     spoilt
    0.83
     Enquiry
    0.81
     ontological
    0.81
     Whilst
    0.81
     debugging
    0.80
    Whilst
    0.80
     equilibria
    0.80
    POSITIVE LOGITS
     administrat
    1.04
    administrat
    0.98
     federally
    0.95
    grandfather
    0.90
     retroactive
    0.89
     grandfather
    0.86
     mand
    0.86
     mandated
    0.85
     retro
    0.82
     instit
    0.82
    Act Density 0.305%

    No Known Activations