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

    Neuronpedia

    INDEX
    Explanations

    eject, dispense, extract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     العنوان
    0.48
     ї
    0.48
    s
    0.46
     Career
    0.45
    的
    0.44
     Volume
    0.44
    ീയ
    0.44
    ä
    0.44
     ఉందని
    0.44
    ö
    0.44
    POSITIVE LOGITS
     droplets
    0.49
     ejec
    0.47
     eject
    0.47
     droplet
    0.46
     dispense
    0.46
     cilia
    0.46
     say
    0.46
     alterations
    0.45
     illicit
    0.45
     nonlocal
    0.45
    Act Density 0.000%

    No Known Activations