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

    Neuronpedia

    INDEX
    Explanations

    Thank you goodbye

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arbitrage
    0.46
     calibration
    0.45
     checklists
    0.44
     broiler
    0.44
     shoreline
    0.44
     chloroplast
    0.43
     ansatz
    0.42
     calendars
    0.42
     roadblocks
    0.42
     calibrations
    0.41
    POSITIVE LOGITS
    Actually
    0.46
    Okay
    0.45
    Еще
    0.44
    Even
    0.43
    Explore
    0.43
    eka
    0.43
    au
    0.42
    Interestingly
    0.42
    Aut
    0.41
    Apparently
    0.41
    Act Density 0.003%

    No Known Activations