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

    Neuronpedia

    INDEX
    Explanations

    action or choice followed by outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frustrated
    0.48
     fundamentally
    0.45
    SHOP
    0.45
     shelf
    0.44
     babe
    0.44
     revolve
    0.44
     revolves
    0.44
     handed
    0.43
     spun
    0.43
     conference
    0.43
    POSITIVE LOGITS
    २
    0.52
     Información
    0.47
     Descripción
    0.47
    १
    0.46
    ૨
    0.46
    amię
    0.45
     ",",
    0.45
    ۲
    0.45
     qualche
    0.45
    ඩ්
    0.44
    Act Density 0.004%

    No Known Activations