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

    Neuronpedia

    INDEX
    Explanations

    superlative descriptors indicating quality or trustworthiness

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

    most, best, top

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مباشرة
    -0.42
    Története
    -0.42
     çeşitli
    -0.40
    RRect
    -0.39
     exactement
    -0.38
    Források
    -0.38
     общей
    -0.37
     allgemeine
    -0.36
    iprot
    -0.36
     Nachbarn
    -0.35
    POSITIVE LOGITS
     among
    0.73
     AMONG
    0.61
     amongst
    0.59
    among
    0.59
     parmi
    0.55
    CloseOperation
    0.55
     Among
    0.54
    之一
    0.50
     Amongst
    0.50
     للمعارف
    0.50
    Act Density 0.017%

    No Known Activations