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

    Neuronpedia

    INDEX
    Explanations

    references to physical landscapes and elevation changes

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

    elevation, height, and climbing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     caccia
    -0.36
    PreferredItem
    -0.33
     paixão
    -0.32
    tanleria
    -0.32
     Schicksal
    -0.32
    WebServlet
    -0.31
     exposição
    -0.31
     schermata
    -0.31
     dø
    -0.31
     infancia
    -0.31
    POSITIVE LOGITS
     climbs
    0.77
     maxHeight
    0.75
     height
    0.72
     climbing
    0.71
     mountain
    0.71
     climbed
    0.71
    climb
    0.71
     climb
    0.70
     heights
    0.70
     elevation
    0.68
    Act Density 0.054%

    No Known Activations