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

    Neuronpedia

    INDEX
    Explanations

    descriptors of natural landscapes and terrain types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    types of terrain or ground cover

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anhänger
    -0.52
     purpoſe
    -0.52
    MemoryWarning
    -0.52
     lawan
    -0.50
    Билгалдахарш
    -0.49
     pleaſure
    -0.49
    packung
    -0.49
     supremacy
    -0.49
     citron
    -0.48
     ſhe
    -0.48
    POSITIVE LOGITS
     sandy
    0.89
     wooded
    0.88
     grassy
    0.87
     forested
    0.81
     rocky
    0.78
     snowy
    0.75
    sandy
    0.74
     leafy
    0.68
    snowy
    0.67
     muddy
    0.67
    Act Density 0.014%

    No Known Activations