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

    Neuronpedia

    INDEX
    Explanations

    SQL, orange, ordering, socially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    landi
    0.42
    尕
    0.42
     중심
    0.40
    വസ്ഥ
    0.39
     malam
    0.39
    涷
    0.39
    lans
    0.39
     zgodnie
    0.38
    的区别
    0.38
    ⾼
    0.38
    POSITIVE LOGITS
     individual
    0.45
     California
    0.45
     Liverpool
    0.44
     red
    0.40
     Ukrainian
    0.40
     Cuban
    0.40
    Liverpool
    0.39
     liver
    0.39
     copper
    0.39
     Egyptian
    0.38
    Act Density 0.003%

    No Known Activations