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

    Neuronpedia

    INDEX
    Explanations

    natural landscapes and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bushel
    0.75
    圄
    0.71
     עס
    0.69
    构建
    0.69
    挚
    0.69
    唁
    0.69
    akang
    0.69
    깥
    0.68
    bindung
    0.68
    뿍
    0.68
    POSITIVE LOGITS
     cliffs
    2.05
     waterfalls
    1.85
     cliff
    1.72
     caves
    1.66
     rocky
    1.55
     canyons
    1.54
     waterfall
    1.52
     canyon
    1.48
     jagged
    1.46
     Cliffs
    1.43
    Act Density 0.318%

    No Known Activations