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

    Neuronpedia

    INDEX
    Explanations

    references to the United States in various contexts

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

    "United States" or "United" followed by a state

    np_acts-logits-general · gemini-2.0-flash

    United States

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rboles
    -0.47
    Außerdem
    -0.45
    PerformLayout
    -0.44
    xampp
    -0.42
    momile
    -0.41
    География
    -0.41
    Natürlich
    -0.41
    astéroïdes
    -0.40
     Außerdem
    -0.40
     éste
    -0.40
    POSITIVE LOGITS
     United
    0.63
     San
    0.59
    <bos>
    0.59
    )))),
    0.57
    ientras
    0.56
     Frie
    0.55
    ropolitan
    0.55
     Central
    0.53
    currentTime
    0.52
     Buena
    0.52
    Act Density 0.335%

    No Known Activations