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

    Neuronpedia

    INDEX
    Explanations

    places and environments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mira
    0.91
    Lu
    0.86
    Ron
    0.85
     Lu
    0.81
    kania
    0.81
    Rom
    0.80
    Lor
    0.80
    Aless
    0.80
    Ely
    0.79
    Lora
    0.75
    POSITIVE LOGITS
     Swamp
    0.86
     Mountain
    0.84
     Steel
    0.83
     Desert
    0.81
     Wilderness
    0.80
     Smoky
    0.80
     Buckeye
    0.80
     Passport
    0.77
     Snake
    0.76
     Smoke
    0.76
    Act Density 0.177%

    No Known Activations