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

    Neuronpedia

    INDEX
    Explanations

    names and references to mountain ranges and geographical features

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

    mountains and mountain ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.41
    новниш
    -0.40
     linkovi
    -0.39
    aarrggbb
    -0.38
    yfikacja
    -0.38
     חיצוניים
    -0.38
     sendok
    -0.38
    omet
    -0.36
    home
    -0.35
    CPT
    -0.35
    POSITIVE LOGITS
     mountains
    0.68
    mountains
    0.67
     Mountains
    0.66
     hills
    0.59
    Mountains
    0.56
     HILLS
    0.53
     mountain
    0.53
     Hills
    0.52
     Andes
    0.48
    mountain
    0.47
    Act Density 0.076%

    No Known Activations