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

    Neuronpedia

    INDEX
    Explanations

    country and nationhood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     መጠቀም
    0.81
    <unused2019>
    0.80
    <unused713>
    0.77
    踺
    0.77
    <unused1058>
    0.76
    எல்
    0.75
    <unused226>
    0.75
    എസ്
    0.73
    ó
    0.73
    et
    0.72
    POSITIVE LOGITS
     iodide
    0.63
    마
    0.61
    است
    0.59
    جو
    0.58
    国
    0.58
     the
    0.57
    ود
    0.56
    ان
    0.55
    لى
    0.55
    0.55
    Act Density 0.074%

    No Known Activations