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

    Neuronpedia

    INDEX
    Explanations

    dog terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    匏
    0.63
     रुझ
    0.55
    "},
    0.55
    өн
    0.55
    цией
    0.54
    ិនបើ
    0.54
     있고
    0.53
     ஆண்டுகளாக
    0.53
    ITIVE
    0.53
    ్రియ
    0.52
    POSITIVE LOGITS
     puppy
    0.61
    喿
    0.61
     canine
    0.59
     superman
    0.58
    Related
    0.55
    Sire
    0.55
    Frederick
    0.55
    irut
    0.55
    wast
    0.54
    ata
    0.53
    Act Density 0.001%

    No Known Activations