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

    Neuronpedia

    INDEX
    Explanations

    references to mountains and their geographical features

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

    mountain ranges and geographical features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ArrowToggle
    -0.49
    참고
    -0.47
    
    -0.41
    UserScript
    -0.41
    円
    -0.40
    rawDesc
    -0.38
    XDECREF
    -0.36
    cibles
    -0.35
     disambiguazione
    -0.35
    fär
    -0.35
    POSITIVE LOGITS
     mountains
    0.68
     Mountains
    0.66
     mountain
    0.64
    mountains
    0.60
     Mountain
    0.58
    Mountains
    0.57
     montañas
    0.54
    Mountain
    0.53
     Mount
    0.52
     Mt
    0.50
    Act Density 0.132%

    No Known Activations