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

    Neuronpedia

    INDEX
    Explanations

    imagine pleasant living spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ворю
    0.44
    optimal
    0.43
    Columbus
    0.40
    San
    0.40
     enriching
    0.39
    險
    0.39
     optimally
    0.39
     optimal
    0.39
     companionship
    0.39
    Available
    0.39
    POSITIVE LOGITS
     forgot
    0.46
     dreamed
    0.44
     stroll
    0.44
     admire
    0.43
     Cooking
    0.42
     cooking
    0.42
     delighted
    0.42
     gost
    0.42
     delight
    0.41
     Forgot
    0.41
    Act Density 0.007%

    No Known Activations