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

    Neuronpedia

    INDEX
    Explanations

    references to locations and geographical entities

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

    Prepositions "in" and "at"

    np_acts-logits-general · gemini-2.0-flash

    Bahamas locations and standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lebanon
    -0.59
    Lebanon
    -0.59
     sri
    -0.57
     Sikkim
    -0.55
     Beirut
    -0.55
    Personendaten
    -0.54
    especie
    -0.54
    Kerala
    -0.53
     Kerala
    -0.52
     Lebanese
    -0.52
    POSITIVE LOGITS
     Bahamas
    0.85
    Baha
    0.84
     Nassau
    0.76
     Baha
    0.75
     Ba
    0.74
     baha
    0.70
    baha
    0.70
    Nassau
    0.69
     Aba
    0.65
    nass
    0.61
    Act Density 0.064%

    No Known Activations