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

    Neuronpedia

    INDEX
    Explanations

    objectification and parts of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skier
    0.58
     wint
    0.58
     gehalten
    0.57
     Greatest
    0.56
    あす楽
    0.55
     restraint
    0.55
    NO
    0.55
     Chapel
    0.54
     jue
    0.54
    ەند
    0.54
    POSITIVE LOGITS
    diaz
    0.64
    ief
    0.61
     feuilles
    0.58
     टें
    0.58
    ahan
    0.58
    бу
    0.56
    elry
    0.56
     ocz
    0.56
    aciones
    0.56
     কারো
    0.55
    Act Density 0.153%

    No Known Activations