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

    Neuronpedia

    INDEX
    Explanations

    references to locations, particularly cities and regions named "New" or similar

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

    "New" followed by a location

    np_acts-logits-general · gemini-2.0-flash

    new york and similar place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lug
    -0.47
    ichord
    -0.46
     Bouchard
    -0.44
     için
    -0.43
    rån
    -0.43
    WaitGroup
    -0.42
    nameof
    -0.42
     MessageBoxIcon
    -0.42
    AndEndTag
    -0.42
    ILabel
    -0.41
    POSITIVE LOGITS
     InputDecoration
    0.79
     newOwner
    0.74
     york
    0.64
     contextLoads
    0.63
    Carriera
    0.62
     Ανακτήθηκε
    0.61
    New
    0.60
    York
    0.60
    ImageContext
    0.59
     York
    0.59
    Act Density 0.084%

    No Known Activations