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

    Neuronpedia

    INDEX
    Explanations

    geographical names or locations

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

    city names and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.54
     ujednoznacz
    -0.54
     nahilalakip
    -0.52
    verwijspagina
    -0.46
     oseb
    -0.42
     invloed
    -0.41
     Protección
    -0.40
    asteroide
    -0.40
    protoimpl
    -0.40
     undang
    -0.39
    POSITIVE LOGITS
    COUVER
    0.74
     Bombay
    0.69
     Toronto
    0.67
     Montreal
    0.66
    terdam
    0.65
     Glasgow
    0.64
    Bombay
    0.63
     Dublin
    0.63
     London
    0.62
     Amsterdam
    0.61
    Act Density 0.011%

    No Known Activations