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

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     guardar
    0.57
    Software
    0.53
     debounce
    0.52
    ician
    0.51
    bigsqcup
    0.51
    時刻
    0.50
    診
    0.49
     cardinality
    0.49
    تحان
    0.49
    بيق
    0.48
    POSITIVE LOGITS
     deforestation
    1.63
     urbanization
    1.51
     encroachment
    1.46
     bulldoz
    1.44
     construction
    1.41
     pembangunan
    1.39
     encroach
    1.36
     строительства
    1.35
     development
    1.33
     infrastructure
    1.33
    Act Density 0.175%

    No Known Activations