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

    Neuronpedia

    INDEX
    Explanations

    the best / the most

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Yet
    0.73
     jossa
    0.72
     megjelen
    0.71
    Correct
    0.70
    Quest
    0.68
    Sci
    0.67
    yet
    0.66
    Common
    0.65
    Car
    0.64
    Short
    0.64
    POSITIVE LOGITS
     only
    1.11
     recipient
    1.08
     savior
    1.07
     holder
    1.06
     beneficiary
    1.04
     boss
    1.04
     custodian
    0.99
     initiator
    0.99
     reason
    0.99
     originator
    0.96
    Act Density 0.057%

    No Known Activations