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

    Neuronpedia

    INDEX
    Explanations

    references to mills and related structures

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

    towers, forts, churches, landmarks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalColumn
    -0.50
    Citiți
    -0.48
     cherchés
    -0.48
     beginnetje
    -0.48
    ViewFeatures
    -0.48
     насељу
    -0.47
    RTSC
    -0.47
    erialize
    -0.47
     Normdatei
    -0.46
    cinnati
    -0.45
    POSITIVE LOGITS
     lighthouse
    0.91
     Lighthouse
    0.66
     tower
    0.56
     phare
    0.54
    ighthouse
    0.52
     beacon
    0.49
    ligh
    0.48
    tower
    0.41
     ligh
    0.40
     towers
    0.40
    Act Density 0.011%

    No Known Activations