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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations, particularly mountains and regions

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

    mountain ranges and publishers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ingo
    -0.57
    Ingo
    -0.48
     Linea
    -0.41
    faring
    -0.41
     INA
    -0.40
    FDRE
    -0.39
    INSON
    -0.39
     Sporting
    -0.39
    Rodney
    -0.39
     weinig
    -0.38
    POSITIVE LOGITS
     Alps
    2.28
     alps
    1.66
     Alpes
    1.31
    Alpes
    1.11
     alpes
    1.03
     Alp
    0.98
     Alpen
    0.96
    Alp
    0.93
     Himalayas
    0.91
     alp
    0.79
    Act Density 0.002%

    No Known Activations