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

    Neuronpedia

    INDEX
    Explanations

    external drive backup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voiced
    0.78
    Abraham
    0.78
     Aa
    0.77
     siting
    0.77
     validator
    0.75
     voicing
    0.75
     Abraham
    0.74
     legitim
    0.74
     moneys
    0.69
     pound
    0.69
    POSITIVE LOGITS
    operation
    0.75
    output
    0.75
    drive
    0.70
    operate
    0.68
    disk
    0.66
    dauer
    0.66
     Kelu
    0.66
     Operate
    0.65
    Operation
    0.65
    OUTPUT
    0.65
    Act Density 0.001%

    No Known Activations