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

    Neuronpedia

    INDEX
    Explanations

    mountain ranges and peaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    묽
    0.52
    沫
    0.51
     housework
    0.49
    鹌
    0.46
    蒯
    0.46
     travaillons
    0.45
     estup
    0.44
     Baltes
    0.44
    swf
    0.43
    ന്റ
    0.42
    POSITIVE LOGITS
     mountain
    1.63
    mountain
    1.38
     Mountain
    1.33
    Mountain
    1.31
    ⛰
    1.31
     mountains
    1.30
    山
    1.24
    🏔
    1.23
     montagne
    1.23
     پہا
    1.21
    Act Density 0.077%

    No Known Activations