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

    Neuronpedia

    INDEX
    Explanations

    nature appreciation and activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nieruch
    0.41
     Вели
    0.38
     cerc
    0.38
     natural
    0.38
     ng
    0.37
     negro
    0.37
     Happened
    0.37
    ilateral
    0.37
     Alternate
    0.37
     kulturn
    0.37
    POSITIVE LOGITS
    lovers
    0.55
     Conservancy
    0.54
     lovers
    0.52
    lle
    0.51
    photography
    0.49
    loving
    0.48
     hikes
    0.48
    lover
    0.48
     conservation
    0.47
     nurture
    0.46
    Act Density 0.012%

    No Known Activations